Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden, but it does not state whether the operation is read-only, what it returns, whether it has side effects, or how pagination behaves. The noun-phrase description does not even confirm the operation being performed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short, but this is under-specification rather than helpful conciseness. The '[P0]' prefix adds operational noise, and the core semantic content is missing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations, no output schema, four parameters, and a large sibling group, a one-phrase description is far from sufficient. Missing information includes the operation, return behavior, pagination semantics, and the tool's role in the auto-add workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25%, and the description adds no parameter explanations. The meaning of action_id, limit, offset, and auto_add_date in the context of automatic addition is left entirely to inference.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a noun phrase that largely restates the tool name: 'candidates for automatic addition to a promotion.' It names the resource but provides no verb or operation, and it does not distinguish this tool from siblings like ozon_actions_candidates, ozon_action_auto_add_products, or ozon_action_auto_add_delete.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool versus related auto-add or action tools. There is no context, prerequisite, or mention of alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure, yet it only states the core operation. It does not disclose whether removal is destructive or reversible, what happens to goods already participating in the promotion, or idempotency behavior when a product_id is not currently in the auto-add list. The [P0] tag is prioritization metadata, not behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single efficient sentence with the operation stated up front and no wasted prose. The [P0] prefix is minor noise but takes negligible space. The brevity borders on under-specification, but as a standalone conciseness measure the structure is clean and immediately readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-parameter mutation tool with 0% schema coverage and no annotations, the description is too thin. An agent can infer the call shape, but crucial details are missing: what action_id refers to, the response format, and behavior when product_ids are not in the auto-add list. The naming symmetry with ozon_action_auto_add_products partially compensates, but the description alone is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but neither action_id nor product_ids is explained. The words 'goods' and 'promotion' loosely map to product_ids and action_id, and the names are largely self-explanatory, but no additional semantics are provided (e.g., what action_id identifies or what constraints apply to product_ids).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Remove') and a precise resource ('goods from automatic addition to a promotion'), making the operation unambiguous. The removal semantics implicitly distinguish it from the inverse sibling ozon_action_auto_add_products, and the meaning is clear without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives. The description never mentions ozon_action_auto_add_products (the inverse add operation) or ozon_action_auto_add_candidates, nor any conditions that would select one tool over another. An agent must infer usage entirely from the tool name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the conceptual behavior — Ozon will add goods automatically on a given date — but it does not clarify whether this tool creates, lists, or modifies auto-add entries, nor whether it has side effects or requires specific permissions. The absence of a clear operation leaves the tool's behavior ambiguous.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence with no redundant text, and the [P0] priority marker is useful. It is appropriately concise, though its brevity sacrifices operational clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even though the parameter count is small, the tool has no output schema and no annotations, so the description should explain the return value, operation type, and how it relates to sibling auto-add tools. It does none of these. The description is a definitional fragment rather than a complete tool contract, leaving an agent uncertain about invocation semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 50%; limit and offset have no descriptions in the schema or the tool description. The description does not add meaning for action_id or auto_add_date beyond the schema, and it says nothing about how limit and offset affect results. Since the description does not compensate for the undocumented parameters, this is a notable gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource: goods that Ozon will add to a promotion automatically on a specified date. It is semantically specific and understandable in context. However, it lacks an explicit verb like 'list' or 'get', and it does not differentiate itself from sibling tools such as ozon_action_auto_add_candidates or ozon_action_auto_add_delete.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like ozon_action_auto_add_candidates or ozon_action_auto_add_delete. The description does not state expected use cases, prerequisites, or exclusion conditions, so an agent has to infer when it should be invoked.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the core mutation but does not reveal side effects, whether existing prices are overwritten, whether the operation is reversible, or what the response contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence with no wasted words, and the Russian gloss adds clarity for a bilingual context. The [P0] tag is not behavioral content but does not detract from the overall conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations and no output schema, the description is minimally viable but not complete enough for safe invocation. It does not mention how to discover action_id, whether the action must already exist, what happens to existing promo prices, or what result to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It maps 'goods' to products and 'promo price' to action_price, but action_id is left implicit and there is no explanation of the product_id field or the array structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the specific operation ('Add goods to a promotion') and the key value ('given promo price'), which clearly distinguishes it from sibling tools like ozon_actions_deactivate and ozon_actions_list. It does not explicitly contrast with alternatives, but the verb+resource combination is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus ozon_actions_deactivate, ozon_seller_action_products_add, or ozon_action_auto_add_products. There are no mentions of prerequisites, such as needing an existing action or candidate products, and no exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description carries the full burden of behavioral disclosure. It indicates this is a check rather than a mutation, which is useful, but it does not state whether it is read-only, what it returns, whether pagination applies, or any other behavioral constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact line that front-loads the core meaning and includes a useful behavioral clue ('pre-emptive check'). Every word earns its place, and the P0 marker adds prioritization context without bloat.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple: one required parameter with a helpful schema description and no nested objects. The description explains what 'candidates' means, which is the main ambiguity. However, with no output schema and no mention of what the result looks like or how it relates to the action lifecycle, the context is only minimally complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter, action_id, already has a descriptive schema comment ('action id from ozon_actions_list'), so schema coverage is 100%. The tool description does not add parameter-specific meaning beyond that, which matches the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource: candidate goods that Ozon plans to pull into a promotion, and gives the purpose: a pre-emptive check against selling at a loss. It is not tautological and adds meaning beyond the tool name, but it lacks an explicit verb like 'list' or 'get' and does not fully distinguish itself from the similar sibling ozon_action_auto_add_candidates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives such as ozon_actions_products or ozon_action_auto_add_candidates. The phrase 'pre-emptive check' implies a use case, but there are no explicit when-to-use or when-not-to-use instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It only says 'Remove goods', implying a mutating action, but does not disclose whether removal is permanent, immediate, reversible, or dependent on promotion status. This leaves the agent without important safety context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with a concrete example and a helpful Russian gloss. The '[P0]' prefix is minor unnecessary noise, but the core information is front-loaded and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with no output schema and no annotations, the description is minimally sufficient to understand the action. However, it omits workflow context such as how to obtain the action_id or product_ids and what a successful removal returns, so it is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It maps 'goods' to product_ids and 'promotion' to action_id only implicitly, and gives no guidance on where these IDs come from, what formats to expect, or any constraints beyond the schema's raw integer types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Remove goods from a promotion', with a concrete example ('loss-making ones'). This clearly distinguishes it from sibling tools like ozon_actions_activate, which implies adding or activating goods.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'e.g. loss-making ones' gives an implied use case, so an agent can infer when this tool is relevant. However, it does not explicitly name alternatives or state when not to use it, such as when adding goods or discovering promotion candidates.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the disclosure burden. It adds a useful behavioral warning that goods in promos can sell below cost, but it does not state whether the operation is read-only, describe side effects, or clarify what 'pulled in' implies. Some transparency is present, but gaps remain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence with no filler, and the key purpose is front-loaded. The '[P0]' prefix is likely internal priority metadata and adds noise, but the rest is efficient and the Russian gloss is helpful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with zero required parameters and no output schema, the description conveys the core purpose and a critical risk. However, it omits details about response format and what 'may be pulled in' concretely means, so an agent has only a partial picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the single 'view' parameter is fully documented with an enum and explanatory description. The tool description adds no extra parameter semantics, but full schema coverage makes the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists Ozon promotions available now and which goods may be pulled in, using a specific verb and resource. However, it does not explicitly differentiate from closely related siblings like ozon_actions_candidates or ozon_actions_products, leaving some distinction to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance, exclusions, or pointer to alternative tools. 'Available now' implies a time-sensitive listing, but the description does not say when to choose this tool over similar action-related siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure, but it only defines a product state rather than describing what the tool does when called. There is no mention of read-only behavior, return format, pagination, filtering, or side effects—an agent cannot predict the tool's runtime behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words, so it is concise. However, the P0 prefix is nonfunctional, and the extreme brevity results in under-specification rather than effective economy; it is structured as a fragment, not a complete operational statement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, no annotations, and only one parameter, the description must explain what the tool returns or how it behaves, but it only describes the subject matter. An agent cannot determine whether this returns a list of SKUs, details, counts, or requires further calls, making the definition incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already fully documents the single parameter action_id with 100% description coverage, so the description adds no additional semantic meaning beyond the schema. The baseline of 3 applies because the structured schema handles the parameter documentation adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource—goods currently in an active promotion—but does not state a verb or explicit operation; the agent must infer "get/list" from the tool name. It does provide some scope differentiation with "already participating," which hints at a contrast with candidate tools, but the operation itself is left unstated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance is given for when to use this tool versus alternatives like ozon_actions_candidates or ozon_actions_list. The phrase "already participating" weakly implies a distinction from candidates, but there is no direct mention of conditions, exclusions, or alternative tools, leaving the usage context to guesswork.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses an important limitation: there is 'no official method' for this balance. This is useful behavioral context beyond the tool name, but with no annotations, the description still leaves uncertainty about reliability, return format, and failure behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and front-loaded, with the core purpose stated first. The parenthetical Russian translation is slightly redundant but not harmful; overall it remains economical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter tool, invocation is simple, but the absence of an output schema and annotations places more burden on the description to explain what the agent should expect. The description names the result concept but not its shape, units, or reliability, leaving a moderate gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is nothing for the description to explain about inputs. The baseline of 4 applies because parameter semantics are not a concern here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource as the ad account balance and distinguishes it from the related spend-focused sibling ozon_ad_statistics_expenses. It lacks an explicit verb like 'retrieve' or 'get', but 'Ad account balance' plus the tool name makes the intended read operation reasonably clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly directs the agent to ozon_ad_statistics_expenses for spend data, which is a clear alternative for a related but distinct need. It does not fully spell out when to prefer this tool over other ad-related tools, but the balance-vs-spend distinction provides usable context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It reveals a 'max 200' limit, which is useful, but it does not clarify whether the tool is read-only, what happens when more than 200 SKUs are passed, what the response contains, or whether any pagination or rate limiting applies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded with the key concept, and the max limit adds useful information in few words. The parenthetical Russian translation is redundant for an English description but does not materially hurt clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no annotations and no output schema, so the description must provide enough context for safe invocation. It gives the core resource and inputs, but omits the response shape, read-only guarantees, failure behavior, and the precise meaning of the 200-item limit, leaving meaningful ambiguity for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the parameter names campaign_id and skus are self-explanatory. The description reinforces the mapping by saying 'by SKU in a campaign.' However, it does not clarify whether 'max 200' applies to the number of SKUs, the number of returned bids, or something else.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource ('competitive bids by SKU in a campaign') and adds a concrete constraint ('max 200'), making the tool's intent mostly clear. It does not use an explicit verb like 'get' or 'list', and it does not explicitly contrast itself with the sibling ozon_ad_campaign_bids, but the word 'competitive' provides some differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this tool instead of related tools such as ozon_ad_campaign_bids or ozon_ad_min_bids. The description implies a use case but never states when it is appropriate or when an alternative should be chosen.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. 'Start' implies a state-changing mutation, but it does not mention preconditions, side effects such as spending resumption, reversibility, or idempotency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence with a clarifying translation, containing no filler. It is appropriately concise for the limited content, though that content is thin.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, this description is incomplete. It lacks information about required campaign state, what activation does, and what the caller should expect in return.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one required integer parameter, campaign_id, with 0% description coverage. The tool description does not explain what campaign_id refers to or how to obtain it, leaving the parameter's meaning almost entirely implicit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Start an ad campaign' uses a specific verb and resource, and the Russian 'запустить кампанию' reinforces the action. It is clear enough to distinguish from create/stop siblings in intent, though it does not explicitly say it activates an existing campaign rather than creating one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like ozon_ad_campaign_create or ozon_ad_campaign_stop. The description gives no context for choosing this tool over its siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It does disclose the mutating nature ('Update'), the expected payload shape, and the non-obvious unit/format requirement (micro-rubles as a string). However, it does not explain whether existing bids are replaced, any constraints, or what the response contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence: the action and resource come first, followed immediately by the crucial format details. There is no filler, and the micro-rubles example is compact and useful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter mutation this is minimally workable: it identifies both parameters and adds the hardest-to-infer detail (bid units and string format). However, there is no output schema or annotation coverage, and sku formatting plus behavioral effects are left unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides no descriptions and the bids item type is just 'object', so the description must compensate. It does explain bids as [{sku, bid}] and gives a concrete micro-rubles string example, but campaign_id semantics and the sku field type/format remain implicit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Update goods bids in a campaign') and the main resource. It does not explicitly distinguish itself from sibling bid-related tools like ozon_ad_bids_competitive or ozon_ad_min_bids, but the object and verb are specific enough to be understood.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to prefer this tool over related ad-bid tools, nor are any exclusions or workflow prerequisites mentioned. The '[P0]' prefix signals priority, not usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does add a useful non-obvious fact: the budget is sourced from the campaign list rather than a dedicated endpoint. However, it does not disclose return format, side effects, or error behavior, leaving meaningful gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with the key point front-loaded. The parenthetical Russian phrase is redundant with the English text, but this is a minor inefficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-oriented tool, the description gives adequate context about the data source. However, with no output schema and no description of what the tool returns, an agent cannot fully anticipate the result shape or units of the budget value.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain campaign_id beyond what the parameter name already conveys. Since the description adds no value to the parameter semantics, it fails to compensate for the lack of schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (campaign budget) and its provenance (taken from the campaign list), which makes the tool's function reasonably clear as a read/retrieval operation. It lacks an explicit verb like 'get' or 'retrieve', but it is not tautological and is distinguishable from sibling tools like ozon_ad_campaign_budget_update.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The statement 'Ozon has no separate endpoint' explains why this tool exists and implies it is the way to obtain campaign budget data. However, it does not explicitly say when to prefer this tool over alternatives, nor does it mention when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the behavioral burden. It does disclose that this is a PATCH-style mutation and that budgets are in RUBLES, which prevents a common unit error. However, it does not mention side effects, permissions, reversibility, whether daily and weekly budgets can both be set, or what response is returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded, with the core action and HTTP verb in the first clause. The Russian parenthetical 'изменить бюджет' is a minor redundancy, but overall it is efficient and easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given five parameters, no annotations, and no output schema, a one-sentence description is insufficient. It does not explain parameter combinations, required-field behavior beyond schema, prerequisites, failure modes, or the result of a successful update, leaving an agent to guess critical invocation details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40%, but the description adds useful semantics by grouping 'budget' with RUBLES and 'period' with the date parameters. It does not clarify campaign_id beyond the schema, optionality constraints, or whether daily and weekly budgets are mutually exclusive, so the low coverage is only partially compensated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Change campaign budget or period') with an explicit HTTP verb (PATCH), clearly identifying this as a mutation tool for ad campaign budgets. It is distinguished from read-style siblings like ozon_ad_campaign_budget by the verb and wording, though it does not name an alternative directly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus related ad campaign tools such as ozon_ad_campaign_budget, ozon_ad_campaign_stop, or ozon_ad_campaign_activate. The PATCH verb and RUBLES hint imply intent, but no explicit when/when-not conditions or alternative routing are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden and does add meaningful constraint context: allowed placement/strategy enum values, a 2000₽ per-SKU minimum budget, and the fact that goods must be attached separately via ozon_ad_products_add. However, it never states what a successful creation returns (critical given no output schema), whether the campaign starts active or paused, or any side effects beyond the verb 'create'. The trailing '(создать кампанию)' fragment adds noise, not behavioral information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and the constraints are packed into a single dense sentence with little wasted space. But the dangling Russian fragment '(создать кампанию)' merely repeats the opening intent in another language, earns no place, and should be deleted; the long inline enum lists also make the clause harder to scan than a structured breakdown would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a mutating, two-step workflow tool with no annotations and no output schema, so the description alone must cover the call contract — and it omits the most consequential parts: what the response contains (e.g., a campaign ID needed to chain ozon_ad_products_add or ozon_ad_campaign_activate), and how the two optional budget parameters satisfy the stated 2000₽ minimum. An agent can invoke it on blind faith but cannot verify the outcome or safely chain the next call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 40%, and the description compensates by enumerating the valid values for strategy and placement — two parameters the schema leaves entirely undescribed — and by adding a budget floor ('Min budget 2000₽ per SKU'). It does not clarify whether daily_budget_rub and weekly_budget_rub are alternatives or how the per-SKU minimum maps to them, and the required title parameter receives no naming guidance. Still, the added enum and budget semantics go well beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource statement — 'Create a CPC Trafarety campaign' — and sharpens scope with 'the only type creatable via API,' which distinguishes it from the dozens of other ad-campaign lifecycle tools in the sibling list (list, stop, activate, budget_update). The intent is unambiguous even without the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly routes the follow-up step: 'add goods via ozon_ad_products_add,' so an agent learns that creating a campaign alone does not complete the ad setup workflow. The 'only type creatable via API' clause sets a when-not boundary against other campaign types. It stops short of explicitly contrasting with campaign lifecycle siblings like ozon_ad_campaign_activate or ozon_ad_campaign_stop, which remain implicit from context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of disclosing behavior, but it only states what the campaign contains rather than what the tool does. It does not reveal whether the operation is read-only, requires special authorization, or has side effects like creating or modifying objects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and avoids filler, with the key resource phrase front-loaded. However, it is under-specified: it names a resource without stating an action, so brevity comes at the cost of clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, no annotations, and a single undocumented parameter, this description is not complete enough for an agent to invoke it correctly. It does not say whether the result is a list, what fields are returned, or how the goods and bids are structured.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema documents a single required campaign_id with no description, and schema coverage is 0%. The phrase 'inside an ad campaign' weakly ties campaign_id to the campaign context, but it does not specify what format or identifier is expected or that campaign_id selects the campaign whose goods and bids are returned.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as goods and bids within an ad campaign, which adds meaning beyond the tool name and hints at a combined product/bid view. However, it lacks a verb, so an agent cannot tell whether this fetches, updates, or manages those objects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to prefer this tool over siblings such as ozon_ad_campaign_products or ozon_ad_campaign_bids. The only contextual clue is 'inside an ad campaign', which is not enough to select among the many ad-campaign tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the burden of behavioral disclosure. It only names the content ('goods and bids') and scope ('in a campaign'), without stating that it is a get/list operation, how pagination works, or whether it has side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is short, but this is under-specification rather than effective conciseness. The Russian parenthetical is redundant and no essential operational detail is included.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations, no output schema, and an undocumented page parameter, the description is far from complete. It does not communicate return structure, pagination behavior, or the selection semantics needed to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no parameter meaning beyond the schema. The word 'campaign' only restates campaign_id, and the page parameter is entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as goods and bids belonging to a campaign, but it contains no verb to signal read versus write behavior. It also does not distinguish itself from siblings like ozon_ad_campaign_objects or ozon_ad_campaign_bids.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool or when to prefer an alternative. With many ad-campaign sibling tools, an agent cannot tell whether this should be chosen over related tools for products, bids, or campaign objects.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of disclosing behavior. It adds useful micro-ruble conversion and enum values, but does not state whether this is a read-only retrieval, what the response contains, whether pagination applies, or how the view parameter changes behavior beyond the schema note.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and dense—one line covers budgeting units and the key enums without wasted words. However, it is somewhat cryptic and lacks the explicit operation statement that would make it a model of concise clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description must do more to orient the agent. It does not confirm the operation type, return semantics, or how the optional filters combine, so an agent would need to rely heavily on sibling names and inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds value by defining the allowed adv_object_type values, the state enum values, and explaining the micro-ruble unit, all of which are missing from the parameter schemas.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (ad campaigns) and adds useful context about budgets, statuses, and filter enums, but it never states the operation with a verb like 'list' or 'get'. 'Ad campaigns' is a noun phrase, so an agent must infer from the tool name and siblings that this is likely a read/list tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this tool versus the many sibling ad-campaign tools, such as ozon_ad_campaign_stop, ozon_ad_campaign_budget, or ozon_ad_statistics. The description provides domain enums but no explicit 'use this when...' or 'alternatives...' context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It communicates a high-level state change and urgency, but does not disclose whether the stop is reversible, what happens to the campaign's ads or budget, or what the response indicates.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler: 'Emergency' signals urgency, 'stop of an ad campaign' states the action, and the Russian gloss adds useful context for the target audience. Every part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no annotations and no output schema, this is minimal but workable: the agent understands what action to take and which parameter is required. However, it lacks information about return values, reversibility, and side effects, which an agent may need for confident invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one required integer parameter, campaign_id, with 0% description coverage, and the description does not mention this parameter at all. The parameter name is self-explanatory, but the description adds no guidance about how campaign_id is used or what values are expected.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Emergency stop of an ad campaign.' This clearly distinguishes the tool from siblings like ozon_ad_campaign_activate and ozon_ad_campaign_create, and the '[P0]' tag reinforces its role as a priority action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Emergency' qualifier implies when the tool should be used, but there is no explicit guidance about when it should be preferred over alternatives such as budget updates or pausing mechanisms. The usage context is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a read-only lookup of minimum bids but does not explicitly state that it is non-mutating, describe the expected response, or mention pagination, authentication, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short and front-loaded, with 'Minimum bids by SKU' conveying the core purpose immediately. The only minor redundancy is the Russian parenthetical 'минимальные ставки', which repeats 'Minimum bids', but it does not meaningfully hurt clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter lookup tool, the description plus schema covers the basic inputs adequately. However, with no output schema and no annotations, an agent is left without information about the return shape or how to distinguish this tool from related bid-related siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does add value by listing valid payment_type values (CPC, CPO, CPC_TOP), which are absent as enums in the schema, and 'by SKU' hints at the meaning of the skus parameter. However, it does not explain the semantics of each payment_type or the expected size/format of the skus array.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as 'Minimum bids by SKU' and enumerates payment_type variants, giving an agent a clear idea of what the tool concerns. However, it lacks an explicit action verb and does not distinguish itself from closely related sibling tools such as ozon_ad_campaign_bids or ozon_ad_bids_competitive.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool instead of the many other ad-bidding tools in the sibling list. There are no conditions, exclusions, or alternative tool references, leaving the selection decision entirely to the agent's inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden. It discloses useful behavior: the 500-item limit and that a missing bid defaults to the competitive bid. However, it does not explain side effects such as whether existing products are preserved, whether duplicate SKUs are handled, or what errors may occur.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with the core operation, then gives the key constraint and bid semantics. The trailing Russian phrase '(добавить товары)' is redundant and does not earn its place, but the rest of the description is efficiently written.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter mutation tool with no output schema and no annotations, the description covers the essential invocation details: target campaign, item limit, and bid format. It is missing context about preconditions, whether the operation is additive or replacing, and response/error behavior, which are relevant for a write operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does meaningfully. It specifies the bids structure as [{sku, bid}], states that bid amounts are in micro-rubles, and explains the fallback behavior when bid is omitted. The campaign_id parameter is not described beyond its name, but the overall parameter guidance is strong.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Add') and resource ('goods to a CPC campaign'), and adds a clear scope limit ('max 500'). This distinguishes the tool from siblings like deletion or bid-management tools, and the campaign type is explicitly identified.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies its use case: adding products to a CPC campaign with optional bids. However, it does not explicitly say when to prefer this tool over sibling tools such as ozon_ad_campaign_products or ozon_ad_products_delete, nor does it state any exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the mutation ('Remove goods') but does not say whether the removal is permanent, idempotent, reversible, or what consequences it has on the campaign.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and front-loaded, which is appropriate for a simple delete tool. The Russian parenthetical is mildly redundant, but it does not add meaningful bloat or hidden structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The core operation is clear enough for an agent to know this tool removes products from a campaign. However, with no annotations, no output schema, and no parameter guidance, the agent is left to infer the exact effect and return behavior. Adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain campaign_id or skus beyond the generic terms 'campaign' and 'goods.' The schema property names and types provide some meaning, but the description adds no parameter-level detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb and resource: 'Remove goods from a campaign.' This makes the core operation obvious and distinguishes it from sibling tools like ozon_ad_products_add. It does not explicitly mention 'ad campaign,' but the tool name and sibling context supply that detail.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance about when to use this tool versus alternatives such as ozon_ad_products_add or ozon_ad_campaign_products. The only inferred usage is from the verb 'Remove,' but no conditions, prerequisites, or exclusions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure and does well by revealing the async nature, approximate latency of 2 minutes, concurrency limit of one report, and campaign/date-range caps. It does not describe the return shape, but it discloses several important runtime behaviors beyond what the schema shows.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact, front-loaded with the priority marker and purpose, and every sentence carries substantive information. There is no fluff or repetition beyond the parenthetical Russian label, which is minor.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even though the description gives strong constraints, the tool is async with no output schema and no explanation of what the report response contains, how the async flow resolves, or what group_by values are valid. An agent is left with significant uncertainty about calling the tool successfully and interpreting its result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50%, and the description adds useful semantics for campaigns and date range by stating maximum limits. However, group_by remains unexplained, and date_to is only implicitly covered by the overall day-limit constraint, so parameter understanding is only partial.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as providing campaign statistics via an async Ozon report, with explicit operational limits. It does not explicitly distinguish itself from sibling tools like ozon_ad_statistics_daily or ozon_ad_statistics_expenses, but the core purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides practical usage constraints: max 10 campaigns, max 62 days, and one report at a time. However, it does not explicitly state when to use this tool instead of the more specific sibling statistics tools, so the usage guidance is implied rather than fully explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the full burden of behavioral disclosure, but it only says 'daily ad statistics.' It does not explain whether this is a read-only operation, how date bounds are handled, what grouping/period behavior occurs, or what the returned data looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and the key phrase is front-loaded, but the parenthetical Russian translation 'ежедневная статистика' is redundant and adds no value. The brevity is more under-specification than effective conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given three required parameters, no annotations, no output schema, and a cluttered sibling space, the description is far too thin. It does not explain campaign selection, date formats, daily aggregation details, or how this tool differs from nearby statistics tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds no parameter information at all. The agent is left without any explanation of what 'campaigns' contains, what format date_from/date_to use, or what date range semantics apply.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource ('ad statistics') and the daily granularity, so the basic purpose is understandable. However, it is a noun phrase with no verb, and it does not clarify what metrics or aggregation are included, nor does it distinguish itself from sibling tools like ozon_ad_statistics, ozon_ad_statistics_expenses, or ozon_ad_statistics_products.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool instead of the many other ad-statistics tools. There are no stated preconditions, no mention of date constraints, and no alternatives named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden for behavioral disclosure. It only states what data is represented ('spend') and does not describe output format, aggregation, date-range handling, or whether campaign IDs are required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The one-line description is short and front-loaded with the core concept, so there is no wasted text. However, the phrasing is a bare noun phrase rather than a structured instruction, and the English/Russian duplication adds little structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with three required parameters, no output schema, no annotations, and a large cluster of ad-statistics siblings, the description is not complete enough. It states the metric but omits scope, return shape, and selection criteria.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not compensate: it does not explain date_from, date_to, or campaigns, their formats, or their roles. This is a 3-parameter tool with no parameter-level help beyond the raw names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource and metric: ad campaign spend (расходы на рекламу). It is a noun phrase rather than a verb+resource statement, and it doesn't explicitly contrast with sibling tools like ozon_ad_statistics or ozon_ad_statistics_daily, so it misses the top anchor.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool instead of the many related ad-statistics siblings (ozon_ad_statistics, ozon_ad_statistics_daily, ozon_ad_statistics_products). No contexts, exclusions, or alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the synchronous execution behavior and metric scope, but does not mention any campaign filtering constraints, date range limitations, response format, or whether this is read-only. The '[P0]' tag is ambiguous — it could indicate priority, time window, or severity — and is not explained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short sentence plus a parenthetical, no filler words. The core resource (CPC campaign product statistics) and key metrics are front-loaded. However, the Russian phrase adds little for an English-speaking agent and the '[P0]' token is cryptic, so it is not perfectly lean.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-oriented statistics tool with a simple flat schema, the description states the resource, scope, and key output metrics, which is adequate. But with no annotations, no output schema, and zero parameter documentation, an agent still lacks critical invocation details such as date format and campaign ID expectations, so completeness is only partial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for all three parameters. The description says statistics are 'per product' for 'CPC campaigns', which maps roughly to 'campaigns', but it does not explain date_from/date_to formats, that campaigns is an array of campaign IDs, or any constraints. It adds minimal semantic value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it fetches CPC campaign statistics per product, listing the metrics (spend, CTR, CPC, orders, ДРР). It clearly distinguishes itself from the broader ozon_ad_statistics and daily/expense variants, though the Russian phrase 'статистика по товарам' is somewhat redundant.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The '[P0]' prefix signals priority and the 'Synchronous' note implies immediate execution, but there is no explicit guidance on when to choose this over ozon_ad_statistics, ozon_ad_statistics_daily, or ozon_ad_statistics_expenses. The metric list and 'per product' phrasing imply use cases, but no direct comparison or exclusions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden. It does add valuable behavioral context: which metric families are deprecated by Ozon and which ones actually work. However, it does not disclose response shape, pagination behavior (despite a limit parameter), or how metrics are aggregated per SKU, leaving meaningful gaps for an unannotated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each earning its place: core purpose, deprecation warning, and sibling routing. The critical information is front-loaded ('Analytics by SKU' and the working trade metrics) with no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The highest-risk failure modes are addressed: the deprecated metric set is explicitly called out, and the search-position use case is routed to the correct sibling. But with no output schema and no annotations, an agent still lacks expectations for return values, date format requirements, and whether metrics are raw counts or sums — gaps the description should have covered given the absent structured metadata.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema coverage at 40%, only metrics and dimensions have schema descriptions. The description adds real value by warning that session_view, hits_view, and position_category are deprecated — metrics an agent might plausibly guess at since they don't appear in the schema's allowed list. However, date_from/date_to format, range semantics, and limit behavior are undocumented in both the schema and the description, so it only partially compensates for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Analytics by SKU' and enumerates the working metric set (revenue, ordered_units, delivered_units, returns, cancellations), making the resource and scope clear. It also differentiates itself from the sibling ozon_product_queries by stating that tool handles search positions. It stops short of 5 only because the verb is implicit ('Analytics' rather than 'Get/Retrieve'), but the intent is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides an explicit exclusion and alternative: 'For search positions use ozon_product_queries (аналитика).' It also instructs the agent not to use deprecated funnel metrics through the deprecation warning. Lacks explicit contrast with other analytics siblings like ozon_analytics_stocks or ozon_product_rating_by_sku, so it falls just short of comprehensive routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions metric categories (availability, scarcity, liquidity) but does not state that this is a read-only query, what the response looks like, whether pagination or rate limits apply, or whether it returns current snapshots or historical trends. This is a significant gap for a tool with no annotation safety signals.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the tool's purpose and includes the SKU limit. The Russian parenthetical '(аналитика остатков)' is redundant but harmless. It is efficient and readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has low parameter complexity, but it has no output schema and no annotation context, so the description must do more to orient the agent. It gives some sense of the returned analytics, but it does not clarify how this differs from stock-on-warehouse tools, what timeframe or units are used, or what the response structure will be. The definition is incomplete for reliable selection among many similar siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents the single 'skus' parameter as an array of integers for 1-100 SKUs. The description repeats the 1-100 limit and adds only the general context of 'specific goods,' so it does not meaningfully extend the parameter meaning. With 100% schema description coverage, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource ('stock analytics for specific goods' by SKU) and enumerates the analytical dimensions it covers: availability, scarcity, and liquidity. It does not explicitly name or distinguish itself from sibling tools like ozon_stock_on_warehouses or ozon_product_stocks, but the 'analytics' framing conveys a distinct purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. Among dozens of sibling tools covering stock, warehouses, and analytics, the description provides no criteria for choosing this one over simpler stock lookups. The '1-100 SKU' constraint is a parameter bound, not usage context or exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of disclosing behavior. It does not state whether this is a read operation, a list, a lookup, or something else, nor does it describe outcomes, side effects, or return characteristics. The agent cannot predict what invoking this tool will do.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short, but brevity is not conciseness when it omits essential information. It does not front-load a clear purpose or operation, so the single sentence does not earn its place as a useful tool definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even though the tool takes no parameters and has no output schema, the description still fails to convey the core operation or what kind of result the agent should expect. For a simple tool, the minimum requirement is a clear purpose statement, and that is missing entirely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters and the input schema is empty, so the schema already fully covers the parameter surface. The description adds no parameter meaning, but none is required; this is the baseline case where parameter documentation is not the bottleneck.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Brand certificates' is essentially a restatement of the tool name 'ozon_brand_certificates' and provides no verb or operation. It identifies a resource but not what the tool does with it, making it a tautology rather than a functional description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this tool, what scenarios it applies to, or how it differs from related sibling tools like ozon_certificate_list, ozon_certificate_info, or ozon_product_certificates. The agent is left without any decision criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations present, the description carries the full burden of behavioral disclosure, yet it only conveys that this is a mutation. It does not state whether the action is irreversible, what downstream effects approval triggers (e.g., order cancellation or refund), or what happens if an already-approved claim is approved again.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler; the action verb leads immediately. The Russian parenthetical is a redundant translation that adds localization value but no semantic content, which prevents a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool the description is near minimum viable, but with no annotations and no output schema it leaves essential context uncovered: what a cancellation claim is, what approving it does, and when to choose it over the sibling reject/list tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description should compensate, but it mentions neither parameter. The cancellation_id is inferable from its name, but the role of the optional 'comment' parameter — whether it is shown to the buyer, required in certain cases, or purely internal — is entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Approve') and a specific resource ('a cancellation claim'), making the core action immediately clear. The 'cancellation' resource disambiguates it from sibling approve tools (ozon_carriage_approve, ozon_returns_fbs_approve, ozon_discount_approve), though it never explicitly names a sibling for contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to approve versus reject a cancellation, even though ozon_cancellation_reject and ozon_cancellation_list are direct siblings. There are also no stated preconditions, such as the claim being in a pending state, or whether approval is the final step in the flow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden for behavioral disclosure. It does not state whether this is a read-only listing, what data is returned, whether pagination applies, or how the state defaults behave beyond the schema. The state enumeration is useful but not sufficient behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with the core resource, and has no unnecessary filler. The state list and Russian clarification add useful information without bloating the text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations, so the description is the only source for understanding the tool's behavior. It omits return structure, pagination behavior, and the practical meaning of each cancellation state, leaving an agent with only a minimal picture of what will happen when invoked.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%, and the description compensates for the state parameter by enumerating its allowed values, which is genuinely valuable. However, the limit parameter is not described and posting_number is only labeled as 'filter', so parameter understanding remains incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource clearly as buyer cancellation claims and adds the v2 marker, while the tool name supplies the 'list' verb. It is distinguishable from the cancellation approve/reject siblings, though it does not explicitly name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given for when to use this tool versus alternatives, such as ozon_cancellation_approve or ozon_cancellation_reject. The usage is only implied by the tool's name and the claim that it covers cancellation claims.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Reject' implies a mutating action, but the description does not state whether the action is reversible, what side effects occur, whether special permissions are needed, or how the optional 'comment' parameter influences behavior. This is a significant gap for a state-changing tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that is front-loaded with the action. However, it is under-specified for a tool with no annotation support and no schema descriptions. It is terse without being appropriately sized, omitting parameter and usage context that should be present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (two flat parameters, no output schema), but the description still leaves critical gaps: it does not clarify the meaning of 'cancellation_id', the role of 'comment', or what happens after a rejection. Without annotations or schema descriptions, this incomplete context makes it hard for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for missing parameter explanations. It does not explain that 'cancellation_id' identifies which claim to reject, or what the 'comment' field is used for. The agent gets no additional meaning beyond the raw parameter names and types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('reject') and resource ('cancellation claim'), making the action unambiguous. It is clearly differentiated from sibling tools like 'ozon_cancellation_approve' (approve) and 'ozon_cancellation_list' (list). The Russian translation ('отклонить отмену') reinforces rather than confuses the meaning.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool versus the alternatives. The description does not mention the sibling approve/list tools, nor does it state any conditions, prerequisites, or context that would help an agent decide between rejection and other cancellation actions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the core state transition from 'new' to 'formed', but it does not mention side effects, reversibility, required permissions, or response behavior after approval.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence that front-loads the action, resource, and state transition. The parenthetical local-language clarification adds clarity without bloating the text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter approve action, the core invocation semantics are present, but there is no output schema or annotation to fill gaps such as expected response, error conditions, or whether the operation is irreversible.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It does so partially by identifying the target resource ('carriage'), making carriage_id self-explanatory as the carriage to approve, but it provides no detail about where to find the ID or format requirements.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Approve'), names the resource ('carriage'), and gives a precise state transition ('status new to formed'), plus a Russian confirmation ('подтвердить отгрузку'). This makes it clearly distinct from other approval tools (returns, cancellation, discount) and from carriage create/list siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'status new to formed' clause implies the tool is meant for carriages currently in 'new' status that need to be formed, but it does not explicitly state when not to use it or mention alternatives such as ozon_carriage_create or other approve tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden and it does disclose a non-obvious API behavior: an empty body would create a real carriage with Ozon-selected postings, which is exactly why delivery_method_id is required. This goes beyond the schema and warns about side effects. It still does not mention post-creation approval or reversibility, but the key risk is covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no filler. The purpose is front-loaded, and the critical caveat about Ozon's empty-body behavior follows immediately without diluting the main message.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-scalar-parameter create action the description is close, but no output schema exists and the lifecycle is not fully closed: it does not say what the response contains (e.g., a carriage id) or that approval may be required via ozon_carriage_approve, one of its siblings. An agent invoking this tool could stop after creation without completing the workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds real meaning to delivery_method_id beyond the schema's 'from ozon_delivery_methods' by explaining why it is required and what happens if it is omitted. departure_date is already declared RFC3339 in the schema, and containers_count has a default, so the description need not repeat those.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States the action and resource explicitly ('Create an FBS carriage') and adds that it is the replacement for the handover act, which differentiates it from the legacy act-creation flow among siblings. The Russian gloss reinforces the domain mapping without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The replacement phrasing tells an agent this is the current tool for FBS carriage creation rather than the old handover act flow. It also instructs that delivery_method_id must be set to avoid Ozon auto-picking postings. It does not explicitly contrast with carriage_approve or list tools, but the context is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says nothing about whether this is a read-only lookup (only the name suggests it), how pagination behaves via limit/offset, what the response contains, or whether results are ordered or filtered. An agent gets no behavioral context beyond the resource name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler: the first names the resource, the second states its downstream purpose. This is efficient, though the first clause is a noun fragment rather than a complete tool-purpose sentence, so it could be slightly more structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with 2 pagination parameters this is minimally adequate: it names the resource and connects to ozon_carriage_create. But with no output schema and no annotations, the absence of any response-shape or parameter-behavior information leaves notable gaps, and the relationship to the near-sibling ozon_delivery_methods is never addressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description never mentions limit or offset. These are conventional pagination parameters whose names are self-explanatory, but the description adds zero meaning about how they apply to this specific listing — for example, whether offset paginates across delivery methods, carriages, or both.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as delivery methods and their carriages with a Russian gloss, and clarifies the tool's role as the source of delivery_method_id for ozon_carriage_create — this gives an agent a concrete sense of what the tool returns and how it fits the workflow. However, it is a noun phrase rather than an explicit verb ('Lists...'), so the action is only implied by the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The statement 'Source of delivery_method_id for ozon_carriage_create' implies a use case: call this before creating a carriage to obtain a valid delivery_method_id. But it never explicitly contrasts this with the sibling ozon_delivery_methods, nor states when not to use it, so the routing guidance is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden of disclosing behavior. It only names the resource and reveals nothing about side effects, read-only vs. write behavior, return format, error cases, or required authorization. The agent has no information about what invoking this tool actually does.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is short, but this is under-specification rather than conciseness. 'Category attributes (атрибуты категории)' is redundant with the tool name and provides no useful information, so the single sentence does not earn its place in a helpful definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and a two-parameter input schema, the description needed to explain what the tool returns, how the parameters relate to category attributes, and how it differs from nearby category-related tools. None of that context is present, so the definition is inadequate for reliable tool selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description provides no explanation of description_category_id or type_id. The schema names give some hint of meaning, but the description adds no value beyond the raw property names and types. For a low-coverage schema, the description was expected to compensate but does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description repeats the tool name almost verbatim ('Category attributes') and adds only a Russian translation. It names a resource but no verb, so an agent cannot tell whether this tool retrieves, searches, or manages category attributes. It also provides no differentiation from closely related siblings like ozon_category_attribute_values or ozon_category_attribute_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this tool, when not to use it, or which alternative should be chosen instead. Siblings such as ozon_category_attribute_values and ozon_category_attribute_search exist, but the description does not help an agent distinguish their purposes or choose among them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden of behavioral disclosure. It only implies a read-only search but does not explain matching behavior, result format, pagination, or any other operational details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short, but this is under-specification rather than effective conciseness. It does not provide enough information to justify its brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With three required parameters, no annotations, no output schema, and no parameter explanations, the description is far too minimal for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description mentions no parameter semantics. The three required parameters (value, attribute_id, description_category_id) are left entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb and resource: 'Search attribute values'. This is specific enough to indicate the tool is for finding attribute values, though it does not distinguish it from sibling tools like ozon_category_attribute_values.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus ozon_category_attribute_values or other category-related tools. No context, prerequisites, or alternative recommendations are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description itself carries the full burden of behavioral disclosure. It merely names the resource and does not state whether the operation is read-only, whether pagination or limits apply, what data is returned, or any side effects. The agent is left with no behavioral information beyond the tool's name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short, but this is under-specification rather than genuine conciseness. The English phrase and Russian translation repeat the same idea, adding no distinct information, and the single sentence does not earn its place by conveying actionable content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, no annotations, and zero parameter documentation, the description provides almost none of the context needed to invoke this tool correctly. An agent does not know what the response looks like, how limit behaves, or how description_category_id and attribute_id should be obtained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for all three parameters: description_category_id, attribute_id, and limit. It does not mention any of them or explain how they relate to the returned attribute values, leaving their meaning entirely to schema field names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as category attribute values and provides the Russian translation, which makes the basic purpose reasonably clear in the context of the Ozon API. However, it uses a noun phrase rather than a verb+resource construction, and does not explicitly differentiate itself from sibling tools like ozon_category_attributes or ozon_category_attribute_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance whatsoever about when to use this tool versus alternatives such as ozon_category_attributes or ozon_category_attribute_search. The description gives no context about which scenario requires attribute values specifically.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full behavioral burden. It adds genuinely useful context beyond the schema by disclosing the scale (9,800 nodes), implicitly warning that fetching the whole tree without search/depth is expensive, and framing search as the narrowing mechanism. However, it does not disclose what happens when called with no arguments, how results are structured, or how depth and search interact when combined.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no waste: the first establishes identity, the second delivers the navigation logic. Every word earns its place and the key behavior (tree size and two usage modes) is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two optional, fully documented parameters, the description covers identity, scale, and both usage modes. Since there is no output schema, the response shape of the tree is left implicit, and the combined depth+search case is not addressed, but these are minor gaps for a straightforward lookup tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so per the baseline the description need not re-document the parameters. The description adds modest semantic value by tying the parameters to usage intent ('pass search to find a category, or depth to go deeper'), but provides no extra detail above the schema's own descriptions of depth levels and case-insensitive search.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies a specific resource (the Ozon category tree), states its size (9,800 nodes), and explains what the tool lets you do (find a category or go deeper than top level). It is easily distinguished from siblings since no other tool covers the category tree itself, though the fetch/get verb is implied rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives concrete usage guidance: use 'search' when you need to find a category, use 'depth' when you need to go deeper than the top level. It explains both navigation modes clearly, but does not explicitly discuss when not to use this tool or name alternatives, since the category-tree resource has no true sibling overlap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description must carry the behavioral burden. It discloses nothing about whether the call is read-only, what response shape to expect, whether a missing certificate errors, or any side effects. The phrase 'details' only implies a lookup.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is short, but mostly redundant: the Russian parenthetical repeats the English phrase and no useful information is front-loaded. This is under-specification rather than effective conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description should at least state what kind of certificate this is and how the ID is obtained. It does neither, leaving real ambiguity among several certificate-related sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the description adds no guidance about certificate_id, such as its source, scope, or validation rules. Only the parameter name and integer type hint at its meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Certificate details' merely paraphrases the tool name (info -> details); it does not state an explicit action or identify what kind of certificate this covers. It does not distinguish ozon_certificate_info from siblings like ozon_certificate_list, ozon_brand_certificates, or ozon_product_certificates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this tool, how it relates to ozon_certificate_list or other certificate tools, or what prerequisite ID to use. An agent must guess the intended flow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure, but it is only a noun phrase restating the name. It doesn't state whether the operation is read-only, what the response contains, whether the status parameter filters results, or any other observable behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short, but this is under-specification rather than effective conciseness. The parenthetical Russian translation adds no information, and no useful details are front-loaded because none exist.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given one undocumented parameter, no output schema, no annotations, and a large sibling list with overlapping certificate concepts, the description is completely inadequate. An agent cannot correctly select or invoke this tool with only 'All certificates (сертификаты).'

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single 'status' parameter has no description in the schema. The description never mentions 'status' or explains what values it accepts, so an agent has no way to understand how the parameter affects the tool's behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'All certificates (сертификаты).' essentially restates the tool name 'ozon_certificate_list' without adding meaning. It fails to specify which certificate domain is covered, making it indistinguishable from siblings like ozon_brand_certificates and ozon_product_certificates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. The presence of sibling tools such as ozon_brand_certificates, ozon_product_certificates, and ozon_carriage_delivery_list makes this omission significant, yet the description offers no context, exclusions, or alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure, and the only behavioral implication is that this is a read/history operation rather than a send operation. There is no mention of pagination, message ordering, what the default limit of 50 controls, response format, or any constraints. The description adds essentially no behavioral transparency beyond what the name already implies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, but this is under-specification rather than conciseness. The Russian parenthetical '(история чата)' is pure duplication that adds no value for an agent, while genuinely useful information about parameters, behavior, and use context is absent. Every token is spent restating the name instead of earning its place with new content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool's surface complexity is low (2 params, 1 required, no nested objects), which lowers the bar, but with no annotations, no output schema, and 0% parameter coverage, the description is the sole source of context. It leaves unanswered what the return value looks like, where chat_id originates, and how limit behaves, making the tool insufficiently specified for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description is the only possible source of parameter meaning, and it provides none. It does not explain that chat_id identifies whose chat history to fetch or where a valid chat_id comes from (e.g., ozon_chat_list), nor what limit governs (number of messages, page size). The description fails entirely to compensate for the uncovered schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Chat message history (история чата)' is a near-direct restatement of the tool name in English and Russian, adding only the word 'message' and nothing else. It names the domain (chat) but supplies no explicit verb, no scope, and no differentiation from sibling chat tools like ozon_chat_updates, ozon_chat_list, or ozon_chat_read. This functions as a tautology rather than an informative definition.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance about when to use this tool versus the several chat-related siblings (ozon_chat_list, ozon_chat_updates, ozon_chat_read, ozon_chat_start). An agent has no way to determine whether this fetches a full transcript, polls for new messages, or overlaps with ozon_chat_updates, so tool selection is left entirely to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether the operation is read-only, what data the chat list contains, how pagination behaves, or what authorization is needed. The unread_only hint adds some semantic context but overlaps with the parameter schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and free of filler, and it leads with the resource name. However, it is a fragment plus one parameter hint rather than a complete, self-contained explanation, so the brevity sacrifices useful content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and a large family of similar chat siblings, this description is not complete enough. It omits what the returned chat list looks like, how page_size works, and when to select this tool over chat_history or chat_updates. An agent could invoke it but would remain uncertain about the result shape and alternatives.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the bare parameter names. It clarifies unread_only=true filters for unread chats, but says nothing about page_size, its default, bounds, or pagination behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource ('Buyer chats (v3)') but never uses an explicit verb like 'list', so the action mostly comes from the tool name. It also does not differentiate this tool from the sibling chat tools such as ozon_chat_history and ozon_chat_updates, leaving an agent to infer the exact scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage guidance is 'unread_only=true for unread ones', which describes a filter option rather than when to choose this tool. No mention is made of when to prefer chat_history, chat_updates, or chat_read, and no prerequisites or exclusions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description must carry the full transparency burden. It reveals only the surface action and does not mention side effects, idempotency, whether the operation is reversible, or any impact on the chat's messages.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler, and the Russian gloss directly clarifies the English action. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter state-mutation tool, this is minimally viable: the agent knows the action and the required ID. However, with no output schema, no annotations, and no detail on response or side effects, it is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain chat_id's format, provenance, or expected values beyond the property name itself. The tool name and description make the general meaning obvious, but the description adds no parameter-level detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a clear verb and resource: 'Mark a chat as read' (пометить прочитанным). This distinguishes it from sibling chat tools like ozon_chat_list, ozon_chat_history, and ozon_chat_send because it names a specific state-changing action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The one-line description implies the tool should be used when a chat needs to be marked as read, but it provides no explicit when-to-use guidance, exclusions, or comparison with alternatives such as ozon_chat_updates.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states that a message is sent, with no mention of authorization requirements, side effects, idempotency, message limits, or what happens on failure. For a mutating action, this is a meaningful transparency gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded with the core action. The parenthetical Russian translation is slightly redundant but harmless. It earns a high score for brevity, though it uses that brevity at the expense of behavioral detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with no output schema and no annotations, the description is minimally sufficient to guess the intended call. Still, it lacks any context about chat_id provenance, constraints on text, or response behavior, so it is not fully complete for an agent operating independently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, and the description does not explicitly document chat_id or text. However, the tool name and description make the semantics of the two string parameters reasonably inferable: chat_id identifies the chat and text is the message content. The description adds minimal but non-zero meaning beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Send a chat message') on a clear resource, which distinguishes it from most of the large sibling list. It does not explicitly contrast with the closely related ozon_chat_send_file, but the message/text framing makes the text-based intent reasonably clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus chat_send_file, chat_start, or chat_reply, nor any prerequisites such as needing an existing chat_id. Usage context is entirely absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action and does not mention side effects, supported file types, size limits, authentication requirements, or what the API returns, which is a significant gap for a mutating operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and front-loaded with the essential action. The parenthetical Russian translation adds slight redundancy but does not significantly harm clarity, so the structure is appropriately terse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of annotations, output schema, and parameter descriptions, the one-line description is not enough for confident invocation. An agent still needs to infer parameter semantics and the operational behavior of the call, especially because this is a mutating action.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not compensate for the undocumented parameters. The meanings of chat_id, file_url, and file_name are left entirely to inference, with no guidance on expected formats, URL accessibility, or naming conventions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the action ('send'), the object ('a file'), and the destination ('a chat'). It is distinct from sibling tools like ozon_chat_send by foregrounding the file payload, so an agent can identify this tool's purpose without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use case is implied: use this tool when a file needs to be sent into a chat. However, there is no explicit when/when-not guidance or mention of alternatives such as ozon_chat_send for text messages, so the guidance is minimal rather than instructive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Start a chat' suggests a mutating action, but the description does not state whether it creates a new conversation, requires an existing chat, has side effects, or what the response contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with no filler, and the key resource ('posting') is front-loaded. However, its brevity comes at the cost of substantive guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no output schema and no annotations, the description is too sparse. It does not explain the result of starting a chat, whether a chat may already exist, or how this differs from related chat tools, leaving an agent with insufficient context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for the undocumented posting_number parameter. The phrase 'about a posting' weakly links the parameter to the tool's purpose, but it does not explain the meaning, format, or expected value of posting_number beyond its name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Start a chat') and resource ('about a posting'), with the Russian equivalent for clarity. It is reasonably distinguishable from sibling tools like ozon_chat_send or ozon_chat_history, though it does not explain what 'start' returns or implies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as ozon_chat_send, ozon_chat_list, or ozon_chat_read. The description implies it is used for initiating a chat about a posting, but does not clarify prerequisites or edge cases like existing chats.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of disclosing behavior. It does not state whether this operation reads or mutates data, what kind of 'updates' are returned, how polling or pagination works, or what side effects occur. The description is essentially empty of behavioral information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is short, but this is under-specification rather than effective conciseness. A two-word phrase that adds no operational meaning does not earn its place, and there is no structured presentation, ordering, or contextual detail to help an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations, no output schema, and a single undocumented parameter, the description is far too thin. It does not explain the tool's purpose, the meaning of the limit parameter, the expected output, or the typical invocation context. An agent cannot correctly invoke or evaluate this tool based on the provided definition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain the meaning of the 'limit' parameter beyond what the schema already shows. It is unknown whether limit caps the number of returned updates, controls a fetch size, or serves some other purpose. The description adds no value for parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Chat updates (обновления чатов)' is a noun phrase that merely restates the tool name in English and Russian. It lacks a specific verb such as fetch, list, or poll, so it does not state what the tool actually does. It also provides no distinction from sibling chat tools like ozon_chat_history or ozon_chat_list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to call this tool versus any of the many chat-related siblings (ozon_chat_list, ozon_chat_history, ozon_chat_send, ozon_chat_read). An agent has no basis for selecting this tool over its alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'company info' and says nothing about side effects, authorization, rate limits, or what calling the tool does beyond a vague retrieval implication.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short but largely restates the tool name and redundantly repeats itself in English and Russian. It is under-specified rather than efficiently informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no parameters the call itself is trivial, but with no output schema the description should clarify what company information is returned. It does not, leaving the expected result ambiguous.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the input schema is fully covered and there is no parameter meaning for the description to add. The zero-parameter baseline of 4 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource as the seller's company information, which gives some scope, but it is a noun phrase with no verb and no specific aspects of the information. It is vague and does not distinguish this tool from related Ozon info tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives, and no exclusions or prerequisites are mentioned. The large sibling list contains related tools, but the description provides no help in selecting among them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only names a resource and gives no indication of side effects, read-only behavior, response shape, rate limits, or required prerequisites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is extremely short, but this is under-specification rather than effective conciseness. It lacks the actionable content needed for a tool definition, so brevity does not earn credit here.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no behavioral detail, so the agent cannot know what data this tool returns or what 'tariffs' refers to in practice. The zero-parameter schema limits risk, but the description is still incomplete for reliable selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters and the schema has no properties, so there is no parameter documentation burden on the description. The baseline of 4 applies because no parameter semantics need to be clarified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Company tariffs (тарифы).' essentially restates the tool name without adding a verb or action. It identifies a resource but does not state whether the tool retrieves, updates, or configures tariffs, and it does not differentiate the tool from its many siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool, what problem it solves, or how it relates to sibling tools. An agent selecting among over a hundred Ozon tools receives no context for choosing this one.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It explains that the tool reports steadily failing tools and interprets this as an API change, but it does not say whether the data is live or cached, how it is collected, or any limitations. The zero-parameter, diagnostic nature makes the risk low, so this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: it opens with a priority marker and the core purpose, followed by a clear statement of what the tool reports. The parenthetical Russian word and the redundant 'No parameters' add minor noise, but overall every sentence is brief and purposeful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter diagnostic tool with no output schema, the description provides the essential context: what it reports (which MCP tools fail) and why that matters (signals an Ozon API change). It does not detail the output structure or data freshness, but the low complexity and lack of parameters make this a reasonably complete definition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already shows zero properties, and the description simply repeats 'No parameters', adding no new semantic information. With schema coverage at 100% and no parameters to document, the baseline of 4 for zero-parameter tools is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's subject ('Tool degradations') and its exact function: listing MCP tools that previously worked and now fail steadily, signalling an Ozon API change. This makes it unmistakably distinct from its many sibling tools, which all target specific Ozon business operations, while this is a meta/diagnostic tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The [P0] prefix and the phrase 'signalling an Ozon API change' imply the intended use case (investigate when tools are failing), but the description never explicitly says when to call this tool versus alternatives or when not to use it. 'No parameters' hints at a simple status check, but no explicit routing guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of disclosing behavior, but it only names a resource. It does not describe whether this is a read-only lookup, what data is returned, how pagination works, or any side effects, leaving the tool's behavior almost entirely opaque.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, but this is under-specification rather than effective conciseness. A single noun phrase does replace verbose content, but it fails to earn its place because it conveys no actionable information about the tool's purpose or behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Even though the tool surface is simple with one optional parameter, the complete absence of purpose, return behavior, and relationship to sibling delivery/carriage tools makes the description inadequate. An agent cannot correctly decide to invoke this tool based on the provided context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one parameter, 'limit', with 0% schema description coverage, and the description adds no explanation of what 'limit' controls or how it relates to delivery methods. The description contributes no semantic value beyond the parameter name itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Delivery methods (методы доставки).' is essentially a translation of the tool name and lacks any verb indicating what action is performed. It does not state whether the tool lists, retrieves, or manages delivery methods, and it does not differentiate this tool from sibling tools like ozon_carriage_delivery_list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no indication of when to use this tool or when to prefer a sibling alternative. There is no mention of context, prerequisites, or exclusions, so an agent has no guidance on selecting this tool over related delivery/supply tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral disclosure burden. It reveals it makes 'light real requests across 12 Seller API categories', indicating live network activity, and explains the diagnostic purpose. However, it doesn't disclose return format, potential side effects, auth needs, or rate-limit impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One compact, front-loaded sentence with the priority label '[P0]' and the trigger condition first. Every clause adds distinct information; the Russian parenthetical is redundant but harmless.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-param, no-output-schema diagnostic tool, the description covers what it checks, that it makes live requests, and when to run it. It does not describe the result format or how to interpret failure output, but that gap is modest given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so there is no parameter meaning the description must add. Schema coverage is effectively complete and the description is not required to document arguments.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description names a specific verb+resource: full self-diagnostics, and concretely enumerates what it covers: host availability, light real requests across 12 Seller API categories, Performance API key check. It clearly distinguishes itself from the many sibling Ozon tools by being the diagnostics entry point.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'Run FIRST when a tool misbehaves — separates a key problem from a category or Ozon API change'. It gives a clear context and diagnostic decision logic, though it does not name specific alternative tools or say when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure, but it only states 'Approve discount requests' without explaining effects, reversibility, required permissions, or what happens after approval. The behavior is implied but not transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the key action. The parenthetical Russian translation is mildly redundant but does not significantly harm clarity or structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and a mutation-style action, the description is too thin. It omits what the approval does at a business level, what the response looks like, and how the 'tasks' input relates to the approval workflow, leaving critical context for an agent to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents the 'tasks' parameter with an inline format listing expected fields. The description adds no parameter-level detail beyond that, which aligns with the baseline for complete schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('approve') and a clear resource ('discount requests'), which communicates the core action. It is distinguishable from siblings like ozon_discount_decline and ozon_discount_tasks by the action and resource, though it lacks explicit differentiation language.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool instead of alternatives such as ozon_discount_decline or ozon_discount_tasks. There is no mention of prerequisites, context, or conditions under which approval should be performed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states that discount requests are declined; it does not disclose whether the action is reversible, whether a seller_comment is required, what side effects occur, or what the response contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. The Russian parenthetical is redundant but not harmful. It is appropriately concise for a simple action, though it could have been slightly more informative without losing efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and no annotations, and the description does not mention return values, result behavior, or whether seller_comment is mandatory when declining. Given the destructive/mutating nature of the action, important context about expected input requirements and outcomes is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already contains a 100% description coverage for the single required parameter 'tasks' with the format '[{id, seller_comment}]'. The tool description adds no further meaning about parameter semantics, so it relies entirely on the schema which is minimally sufficient but not enriched.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Decline') and resource ('discount requests'), and the action is naturally contrasted with the sibling 'ozon_discount_approve' (approve vs decline). It does not elaborate on the exact domain or scope of the discount requests, but the core purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool instead of related siblings like ozon_discount_approve or ozon_discount_tasks. No conditions, prerequisites, or exclusions are provided. The agent must infer usage solely from the verb 'decline'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden for behavioral disclosure. It does not explicitly state that this is a read-only query, does not describe pagination or ordering behavior, and offers no information about what the returned request objects contain. The status list is useful but is more parameter semantics than behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short and contains no filler. Every element — the resource type and the status options — is directly useful. The status list is front-loaded enough to immediately tell the agent what kind of filter is expected.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter list operation, the description provides enough to make a reasonable first call, especially since status values are listed. However, there is no output schema and the description never states what the returned data looks like or how limit interacts with pagination. It also does not connect this tool to the discount approval workflow, which would help an agent understand its role among the sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 50%, with limit documented but status left undescribed. The description compensates by enumerating the allowed status values: NEW, SEEN, APPROVED, PARTLY_APPROVED, DECLINED, AUTO_DECLINED. This adds real semantic value beyond the schema for the status parameter, though it adds nothing about limit beyond what the schema already states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource clearly: buyer 'want a discount' requests, and enumerates the relevant statuses. It does not use an explicit verb such as 'list' or 'get', but the plural noun plus status filter strongly implies a retrieval/list operation. It is distinguishable from sibling actions like ozon_discount_approve and ozon_discount_decline, though it does not name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is used to view buyer discount requests by status, which is a natural precursor to approving or declining them. However, it gives no explicit guidance about when to use it versus alternatives, and does not mention that approval/decline actions are the follow-up operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full behavioral burden. It only conveys a daily time grain and gives no information about return shape, read-only behavior, pagination, or limitations. The agent is left to infer even that this is a retrieval operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.