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

No annotations are provided, so the description carries the full burden. The description implies a write/mutation operation ('apply') but doesn't disclose what the plan application does, whether it's reversible, what side effects occur, or what happens with warnings. The acknowledge_warnings parameter hints at potential destructive or risky behavior, but the description doesn't explain this. This is a significant gap for a mutation 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 extremely concise: two short phrases. It front-loads the core action and the critical consent requirement. However, it's so brief that it sacrifices necessary behavioral detail. Still, for what it does say, it's efficient and well-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?

Given the tool has an output schema and 2 parameters, the description is incomplete. It doesn't explain the plan application process, the role of acknowledge_warnings, what the output represents, or any side effects. The consent requirement is useful but insufficient for an agent to confidently invoke this tool, especially since it appears to be a write operation with potential warnings.

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 doesn't explain what plan_id refers to or what acknowledge_warnings does. The parameter names are somewhat self-explanatory, but the description adds no meaning beyond the schema. The acknowledge_warnings parameter especially needs explanation (what warnings? why acknowledge?).

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 'Применить план' (Apply the plan) clearly identifies the action: executing a previously created plan. It distinguishes itself from siblings like plan_write (which creates the plan) and run_read (which performs read operations). However, it doesn't explicitly name the sibling alternatives, so it loses a point for not fully differentiating itself.

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 states a critical usage condition: 'Только после согласия пользователя' (Only after user consent). This is explicit guidance on when to use the tool. It doesn't explicitly mention alternatives or when not to use it, but the consent requirement is a strong contextual signal that this is a confirmation step after planning.

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 supplied, so the description carries the full burden. It only mentions that it describes parameters, example, and restrictions, but does not disclose whether the operation is read-only, has side effects, requires authentication, or any other behavioral traits. The description is insufficient for safe invocation.

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 (one line), but this is under-specification rather than effective conciseness. It omits critical details that an agent needs, so brevity is not a virtue 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?

Although an output schema exists, the description does not explain what the tool returns beyond vague mentions of 'example' and 'restrictions'. With a single parameter and no behavioral context, the definition is far from complete 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?

The schema has one required parameter 'name' with type string, but the description does not explain its meaning or expected format. Schema description coverage is 0%, and the phrase 'parameters (JSON Schema)' merely repeats the schema structure without adding semantic value.

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 'Action description: parameters (JSON Schema), example, restrictions' which is vague and does not specify a concrete verb or resource. It reads as a template rather than a specific tool purpose, and it does not differentiate from siblings like list_accounts or search_actions.

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. There is no mention of contexts, exclusions, or preferred scenarios, leaving the agent to infer usage from the name alone.

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. It does add useful behavioral context by stating the tool returns recent write operations from the journal, which implies a safe read operation. However, it does not disclose ordering, scoping, or account-filter behavior explicitly.

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 phrase with no filler, and the core meaning is front-loaded. It is appropriately terse, though the brevity sacrifices useful usage and parameter details.

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 and has an output schema, but the description omits when to use it, what the parameters do, and any log-specific behavior. An agent could guess the basics, but the description alone is not complete enough for confident selection and correct parameter usage.

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 or interaction of 'limit' and 'account' beyond their names and defaults. Since the schema itself provides no descriptions, the tool description needed to compensate but did 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 clearly identifies a read operation returning the most recent write operations from the journal, and the tool name reinforces the resource. It is distinguishable from siblings like list_accounts and apply_write, though it does not explicitly differentiate itself from search_actions.

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 search_actions or other siblings. There are no stated exclusions, prerequisites, or alternative conditions; the intended use is only implied by the word 'latest'.

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 must disclose behavioral traits. It mentions 'from discover cache,' indicating the data is cached, and specifies the type of data (active campaigns, balance). However, it does not explicitly state that this is a read-only operation, whether it requires authentication, or any side effects. For a listing tool, read-only is likely, but it is not stated. The description provides some behavioral context but falls short of full transparency.

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 conveys the key data points. It is front-loaded with the source (cache) and the main outputs. It is efficient with no unnecessary words.

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 tool has no parameters and an output schema exists, the description only needs to clarify purpose and usage. It provides some context (what data is returned) but lacks any guidance on when to use it versus siblings. For a simple listing tool, the missing usage guidance is a notable gap. The description is adequate but 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 tool has zero parameters, so the schema is trivially complete. The description does not need to add parameter details. A baseline of 4 is appropriate because no parameter information is missing or ambiguous.

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 lists what the tool returns (accounts from cache, active campaigns, balance) but does not clearly state the action (listing). It is more of a summary of output than a purpose statement. It avoids a pure tautology by adding details, but it is not a specific verb+resource description. The name 'list_accounts' hints at the action, so an agent could infer it, but the description itself is vague.

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 sibling tools (search_actions, describe_action, run_read, plan_write, apply_write, get_operation_log) suggest different operation types, but the description does not differentiate or recommend one. An agent would have to guess based on the name alone.

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 behavioral burden. It conveys that the tool produces a preview and warnings rather than directly applying a change, which is useful, but it does not explicitly state side-effect safety, authorization needs, or 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?

A single compact sentence front-loaded with the verb and key artifacts. There is no filler or repetition, although the brevity comes at the cost of missing input 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?

The output schema likely covers return values, but the description is otherwise incomplete: it does not explain what name/params mean, how the plan connects to apply_write, or any preconditions. For a tool with a free-form params object, this is too thin.

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 meaning to 'name' or 'params'. 'params' is an open object with no documented keys, and 'name' could be an action identifier or something else; an agent cannot reliably construct valid input. The only related term, plan_id, appears as an output artifact, not an input.

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 concrete operation ('prepare a write') and names the artifacts it produces (preview, warnings, plan_id). This distinguishes it at the intent level from apply_write, though it never explicitly names the sibling.

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 verb 'prepare' plus preview/warnings/plan_id implies this is a pre-flight step before apply_write rather than an actual mutation. However, it never explicitly states when to use it vs. alternatives or 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 provided, the description carries the full burden of behavioral disclosure. It only states that the output is Markdown, but says nothing about read-only guarantees, error behavior, permissions, rate limits, or side effects. 'Чтения' implies a read, but this is not explicit.

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 the second sentence about Markdown output provides useful information. However, the first sentence merely restates the tool name, so part of the text is redundant. It is concise but under-specified.

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 0% schema coverage and no annotations, this description is far from complete. It does not explain how to select a value for 'name', what read actions exist, or what 'params' should contain. The output schema exists but cannot compensate for missing invocation guidance.

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 mention the parameters 'name' or 'params' at all. It fails to explain what 'name' refers to, what valid values exist, or how 'params' should be structured, adding zero semantic value beyond the bare schema 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 phrase 'Выполнить действие чтения' is essentially a restatement of the tool name 'run_read', not a specific verb+resource description. It adds that output is Markdown, but does not clarify what read action, resource, or domain it operates on, leaving the purpose vague.

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 siblings like search_actions or describe_action. The description does not mention any prerequisites, alternatives, or selection criteria, so the agent gets no help deciding when run_read is appropriate.

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 disclosure burden. It only says 'search' and lists mode values; it does not state whether the call is read-only, whether permissions are required, or what happens with no matches. The non-mutating nature of search is inferable but not explicit.

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: the operation is stated first and there is no filler. It is terse to the point of being telegraphic, but that still serves conciseness well.

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 and an output schema exists, the description omits query semantics, mode semantics, and how this tool relates to siblings like describe_action or run_read. It is not complete enough for an agent to select and invoke reliably.

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 both parameters. It adds allowed values for mode ('read, write or any') but does not explain what mode means or what the query should contain, leaving query entirely undocumented.

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 ('Поиск' = search) and a resource ('действий каталога' = catalog actions), and it adds the mode filter. It does not precisely define what counts as an 'action' or how it differs from siblings like describe_action, but the core purpose is identifiable.

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 search_actions rather than list_accounts, describe_action, or get_operation_log. The mode values hint at filtering, but no explicit context, 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.