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

No annotations are present, so the description must cover behavior. It describes adding a good but does not disclose side effects (e.g., duplicate handling, permissions, limits, whether the operation is reversible). 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 concise, with a clear docstring structure and a bullet-style Args section. Every sentence is necessary and no redundant information is 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?

Given the low complexity (3 simple parameters, no enums) and the presence of an output schema (though not shown), the description adequately explains the tool's purpose and parameters. It does not describe return values, but output schema likely covers that.

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 explain all parameters. It provides context for each: name (example), unit (example list), price (type hint 'as string', example). This adds significant meaning beyond the schema's types and titles.

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 ('Add a new good') and the resource ('to local catalog'). It uses a specific verb and resource, and naturally distinguishes from siblings like goods_list and goods_remove which handle listing and removal.

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 alternatives, nor any conditions or exclusions. It only describes what it does, leaving the agent to infer usage context from the action 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?

Discloses read-only nature (consistent with readOnlyHint) and specifies return format as JSON array with fields name, unit, price, adding value beyond annotations.

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 essential information front-loaded: purpose first, then return details and alternatives.

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?

Complete for a simple listing tool with no parameters; output schema exists, so return values are covered; no 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?

No parameters, so baseline is 4 per rubric; description adds no further parameter info, but none is needed.

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?

Clearly states it lists all goods from local catalog, distinguishing itself from sibling tools goods_add and goods_remove which are for management.

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 mentions alternatives goods_add/goods_remove for managing, providing clear guidance on when to use this tool.

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?

Annotations already indicate destructive=true; description adds that it operates on 'local catalog', providing context beyond annotations. No contradiction.

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?

Extremely concise: two sentences, front-loaded with the key action and resource, no wasted 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?

For a simple one-parameter tool with output schema, the description covers purpose and parameter adequately. Could mention error handling for missing goods, but not necessary.

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%, but description adds meaning: 'Exact product name to remove' clarifies the exactness requirement, which is crucial for correct invocation.

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 'Remove' and the resource 'good from local catalog', distinguishing it from siblings like goods_list and goods_add.

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 mentions 'by exact name' which implies usage condition, but no explicit guidance on when to use or alternatives. However, for a simple delete tool, this is minimally adequate.

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?

Annotations already declare readOnlyHint=true, so the description adds some value by specifying the default behavior (uses first account if account_id empty). However, no other behavioral traits are disclosed beyond that, such as concurrency, rate limits, or side effects. The description does not contradict annotations.

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 sentences with no wasted words. The purpose is front-loaded in the first sentence. Every sentence adds value without 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?

Given the existence of an output schema, the description does not need to explain return values. It adequately covers the only parameter and the tool's basic purpose. However, it could mention that this is for a specific bank account system or note any prerequisites (e.g., authentication), but overall it is sufficiently complete for a simple read tool with good annotations.

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 0% schema description coverage, the description compensates well by explaining the 'account_id' parameter with an example format and noting the default empty-string behavior. This adds significant meaning beyond the schema, though it could have provided more detail about allowed formats or constraints.

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 gets 'detailed account information', which is a specific resource. It uses a specific verb 'Get' and resource 'detailed account information', but does not explicitly differentiate from sibling tools like 'tochka_balance' or 'tochka_all_balances', which limits clarity slightly.

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. The description does not mention circumstances under which this tool is preferable, nor does it list when not to use it. The only usage hint is about using the first account if account_id is empty, but this is more behavioral than comparative.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds no further behavioral details (e.g., what details are returned, constraints). It is adequate but does not enhance transparency beyond annotations.

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 concise with two sentences. The first clearly states purpose; the second lists a parameter but is not structured. It is efficient but could be formatted better for readability.

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 read tool with one parameter and an output schema, the description provides the essential purpose. It could mention prerequisites or response expectations but is mostly 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 coverage is 0%, so the description must compensate. It only restates the parameter name and adds minimal clarification ('Payment operation ID'), without format or origin details. This is insufficient for full 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 clearly states the tool retrieves acquiring payment operation details, with a specific verb ('Get') and resource. It effectively distinguishes from sibling tools like 'tochka_acquiring_payments' (list) and 'tochka_acquiring_payment_create' (create).

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 on when to use this tool versus alternatives such as 'tochka_acquiring_payments' or other payment-related tools. The description lacks context for selection.

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 only says 'Capture funds', which implies mutation, but does not disclose side effects, idempotency, rate limits, or auth requirements. The annotation 'openWorldHint: true' hints at unknown behavior, but the description adds no additional behavioral context beyond the annotation.

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, consisting of a single sentence and an argument list with no wasted words. However, for a financial capture tool, it may be too terse, missing critical usage context.

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 it has an output schema, the description need not explain return values, but it lacks context about the two-stage flow, prerequisites, and typical usage. This is insufficient for an agent to correctly invoke the tool without additional domain knowledge.

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 0% schema description coverage, the description attempts to define 'operation_id: Payment operation ID', but this adds minimal value over the schema's title 'Operation Id'. It does not specify format, source, or constraints, leaving the agent without adequate guidance.

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 'Capture funds for two-stage acquiring payment', using the specific verb 'capture' and resource 'funds', which distinguishes it from sibling tools like 'tochka_acquiring_payment_create' (create) and 'tochka_acquiring_payment_refund' (refund).

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 usage in a two-stage process (capturing after authorization) but does not explicitly state when to use this tool vs. alternatives like 'tochka_acquiring_payment_create' or the prerequisites for the operation_id. The agent is left to infer the 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?

Annotations only include openWorldHint, no destructiveHint. Description does not disclose mutation side effects, error behaviors, or prerequisites beyond parameters.

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?

Purpose stated concisely; parameter list is structured but somewhat verbose. Could be slightly tighter.

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?

Covers all parameters and alternative tool. Missing info on error handling, return value (though output schema exists), and idempotency. Reasonably complete for a complex 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 coverage is 0%, so description fully explains each parameter with constraints (e.g., length, format, allowed values) adding significant value over 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?

Clear verb+resource: 'Create acquiring payment operation (payment link).' Explicitly distinguishes from sibling tool for payments with receipt.

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 alternative tool for fiscal receipts: 'For payment with fiscal receipt, use tochka_acquiring_payment_with_receipt.'

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 destructiveHint annotation already marks this as state-modifying. The description adds valuable behavioral context: precondition (only APPROVED status) and a constraint (amount must not exceed payment amount). No contradictions with annotations.

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 sentences with no extraneous words. The purpose is front-loaded, followed by parameter details, making it 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?

Given the tool's simplicity (two parameters, output schema exists), the description covers all necessary aspects: purpose, precondition, and parameter constraints. No gaps remain for an agent to invoke 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?

With 0% schema description coverage, the description fully compensates by defining both parameters: operation_id as the payment operation ID and amount as the refund amount with a constraint. This adds meaning beyond the bare schema titles.

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's function: refund an acquiring payment. It also specifies the status condition ('only for APPROVED status'), which distinguishes it from related tools like create or capture. The verb 'refund' and resource 'acquiring payment' are specific.

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 implicitly provides usage context by requiring APPROVED status, but does not explicitly state when not to use this tool or mention alternatives. It is clear but lacks exclusions or comparative 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?

Annotations already provide readOnlyHint=true, indicating a safe read operation. The description adds pagination and filtering details, which are useful but do not contradict annotations. No additional behavioral traits are disclosed beyond what the annotations imply.

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 uses a clear 'Args:' format. It is front-loaded with the purpose and efficiently lists parameters. Minor improvement could be more natural language, but it is well-structured and not verbose.

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 complexity of 5 optional parameters and the presence of an output schema (so return values are not needed), the description covers all parameter meanings, defaults, formats, and allowed values. It is fully adequate for agent use.

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 description provides detailed explanations for all parameters, including default values, date format (YYYY-MM-DD), and allowed status values. This compensates well for the lack of schema descriptions.

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 'Get list of acquiring payment operations,' which is a specific verb and resource. It distinguishes from siblings like 'tochka_acquiring_payment' (single payment) and 'tochka_acquiring_payment_create' (create operation).

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 lists parameters but does not explicitly guide on when to use this tool versus alternatives, nor does it mention when not to use it. However, the context of retrieving a list is clear.

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?

Annotations only have openWorldHint. Description adds parameter constraints (e.g., ttl range, customer_code format) but does not disclose behavioral traits like idempotency, error handling, or authentication requirements beyond the implied creation action.

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?

Structured with purpose, sibling reference, and an 'Args' section listing parameters. Concise given the number of parameters, though could optionally be more tabular.

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?

Covers all parameters and sibling distinction. Lacks description of output/return value and prerequisites (e.g., merchant existence), but overall adequate for a complex 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 0%, but the description fully compensates with detailed explanations for all 17 parameters, including formats, examples, and defaults.

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 'Create acquiring payment operation with fiscal receipt' and explicitly distinguishes from the sibling 'tochka_acquiring_payment_create' for payments without receipt.

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 explicit alternative: 'For payment without receipt, use tochka_acquiring_payment_create.' Though other related tools exist, this single contrast is clear.

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?

Annotations already indicate readOnlyHint=true (safe read) and openWorldHint=true (results may vary). The description adds the context that the registry is for a specific date, which is beyond what annotations provide. No contradictions. Even though it does not detail pagination or response structure, the presence of an output schema compensates for return value documentation.

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 three sentences long, front-loaded with the tool's purpose, and includes only essential information. Every sentence adds value: purpose, prerequisite, and parameter descriptions. No fluff 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?

Given the context signals (2 required parameters, output schema exists, sibling tools cover related functionality), the description is sufficiently complete. It explains the core operation and a critical dependency. The output schema likely documents the return structure, so no further elaboration is needed.

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 has 0% description coverage, so the description carries the burden. It adds brief semantics for both parameters: 'merchant_id: Merchant identifier' and 'registry_date: Registry date YYYY-MM-DD'. The date format hint is valuable, but the descriptions are minimal and could elaborate on acceptable formats or constraints.

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 'Get acquiring payment registry for a specific date' – a specific verb ('Get') and resource ('acquiring payment registry'). It distinguishes from sibling tools like 'tochka_acquiring_retailers' (retrieves merchant IDs) and 'tochka_acquiring_payments' (likely payments), making its unique purpose evident.

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 use 'tochka_acquiring_retailers' to obtain valid merchant_id values, providing a clear prerequisite. It also specifies the date format (YYYY-MM-DD) in the Args section. However, it does not compare with other acquiring tools or describe scenarios where this tool should be avoided.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds the clarification 'merchant points' but no additional behavioral traits beyond what annotations provide.

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?

Single sentence, 7 words, front-loaded with key information. Every word earns its place. No 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?

Given zero parameters and an output schema (present but not shown), the description is complete. The tool's purpose is fully and simply communicated.

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?

No parameters exist; baseline score of 4 applies. Description does not need to add parameter info. The context of retrieving a list is clear from the description.

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?

Clear verb 'Get' and resource 'list of acquiring retailers (merchant points)'. Unambiguous and distinct from sibling tools that deal with payments, invoices, goods, etc.

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 on when to use this tool versus alternatives. However, as a simple list with no parameters, usage is intuitive. Lacks any exclusionary conditions or comparisons with 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, indicating safe read operation with no side effects. The description adds that it returns a JSON array of balances, but does not disclose additional behavioral traits beyond what annotations provide. It does not contradict annotations.

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 three sentences long, with no wasted words. It front-loads the core purpose, then gives usage guidance, then specifies the return format.

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 zero parameters, annotations that cover safety, and an output schema that likely documents the return structure, the description provides sufficient context: what the tool does, when to use the alternative, and the nature of the response (JSON array of balances).

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?

There are zero parameters (schema coverage 100%), so baseline is 4. The description does not need to add parameter information, and it does not miss any opportunity to clarify usage.

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 'Get balances for all accounts at once' with a specific verb (Get) and resource (balances for all accounts). It also explicitly distinguishes from the sibling tool tochka_balance, which is for a single account.

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 says 'For a single account's balance, use tochka_balance', providing a clear alternative and guidance on when to use this tool versus its sibling.

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?

Annotations declare readOnlyHint=true, matching the read operation. Description discloses return structure with field names, adding value beyond annotations. No contradictions.

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 sentences and a bullet list – every word earns its place. Front-loaded with purpose, no fluff.

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?

Simple tool with no parameters and annotations. Description covers purpose, alternative usage, and return structure adequately.

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?

No parameters; schema coverage 100%. Description explains return fields, adding value. Baseline for 0 params is 4.

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 states 'Get bank account balance from Tochka Bank' – specific verb and resource. Also distinguishes from sibling 'tochka_all_balances', which gets all accounts.

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 suggests using 'tochka_all_balances' for all accounts, providing clear when-to-use guidance. No exclusion or prerequisite info, but adequate given simplicity.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds the account default behavior but does not disclose pagination, limits, or error handling.

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 brief and front-loaded with the action, but the 'Args:' section is somewhat redundant given the schema. No wasted 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 an output schema exists and the tool is simple (1 optional param), the description sufficiently covers usage without needing to detail return values.

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 0% schema description coverage, the description explains the single parameter's purpose and default, which is adequate but lacks format or constraints 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 clearly states the verb 'Get' and the resource 'authorized card transactions for account', which distinguishes it from siblings like 'tochka_acquiring_payments' or 'tochka_statements_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 provides a default behavior hint ('Uses first account if empty') but gives no guidance on when to use this tool versus alternatives among the many 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?

Description discloses that the tool 'automatically removes paid ones from tracking,' which is a behavioral trait beyond the 'openWorldHint' annotation. It also explains fallback matching criteria in detail, adding useful 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?

Description is well-structured with bullet points and front-loaded main purpose. Slightly verbose but efficient, no wasted sentences.

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's complexity (two strategies, auto-removal, fallback criteria) and the existence of an output schema for return values, the description is complete and covers all essential behavioral aspects.

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?

Only one parameter 'days' with default 30. The input schema has no description, but the description explains it as 'Statement depth in days for fallback (default 30),' which adds necessary 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?

Description clearly states the tool checks pending invoices for payment and automatically removes paid ones. It distinguishes between two strategies (with/without document_id), which differentiates it from sibling tools like 'tochka_pending_invoices' or 'tochka_track_invoice'.

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 explicit guidance on when to use each strategy (with/without document_id) and fallback criteria. However, it does not explicitly state when not to use this tool versus alternatives, 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?

Annotations already indicate readOnlyHint and openWorldHint, covering the safety and partial result behavior. The description adds no further behavioral insights (e.g., error handling, caching, or side effects), but does not contradict annotations.

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 purpose. It is appropriately sized for a tool with one parameter, but a sentence about the expected result or usage context would improve it without adding bulk.

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's simplicity (one required param, no enums), annotations, and output schema, the description covers the basic interaction. However, it lacks context on what a 'consent' is and how this tool relates to nearby siblings like 'tochka_consents', making it slightly incomplete for an agent with no prior knowledge.

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. However, the description only repeats the parameter name and a generic 'Consent identifier', which is already present in the schema title. No additional meaning or constraints are provided.

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 'Get consent details' which clearly indicates retrieving information about a consent. However, it does not explicitly differentiate from sibling tools like 'tochka_consents' (likely list) or 'tochka_consent_children', but the required consent_id parameter implies a single resource lookup.

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. The description does not mention exclusions, prerequisites, or context such as when to use 'tochka_consents' instead.

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 lacks disclosure of behavioral traits beyond annotations. While annotations indicate readOnly and openWorld, the description does not elaborate on output characteristics, pagination, or any 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 description is a single concise sentence that conveys the essential purpose without extraneous information.

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 read-only tool with one parameter and an output schema, the description is adequate but does not explain the output structure or what constitutes 'child consents'. Some additional context would improve completeness.

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 0% schema description coverage, the description adds value by explicitly stating that consent_id is the 'Parent consent identifier', clarifying its role beyond the schema's 'Consent Id' title.

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 'Get all child consents for a given consent' clearly states the action (Get) and the resource (child consents), and it distinguishes from sibling tools like 'tochka_consent' (single consent) and 'tochka_consents' (list of all consents).

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. The sibling tools suggest various consent operations, but the description does not clarify use cases or exclusions.

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?

Annotations include openWorldHint=true, indicating possible side effects not described. The description does not disclose any behavioral traits beyond creation, such as authorization needs, limits, or effects on existing consents.

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 with an args section. It is efficiently structured with no extraneous information, though could be slightly more polished.

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 existence of an output schema and many sibling tools, the description lacks context about what an API consent is, how to use the created consent with other tools, or any post-creation steps.

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 has 0% description coverage, but the description adds value by providing examples for permissions (e.g., ['ReadAccountsBasic', 'ReadBalances']) and specifying expiration_date_time format (ISO8601). This meaningfully supplements 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 clearly states 'Create a new API consent,' which is a specific verb and resource. It distinguishes from sibling tools like 'tochka_consent' (likely get details) and 'tochka_consents' (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?

No guidance on when to use this tool versus alternatives, prerequisites, or when not to use it. The description only states what it does, without 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?

Annotations already declare readOnlyHint=true and openWorldHint=true. Description adds no further behavioral context beyond a basic listing. No contradiction, but minimal added value.

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?

Single sentence, no wasted words, front-loaded with purpose. Highly concise.

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 and an output schema present, the description is adequate. It could mention that the tool returns a list, but the output schema covers return structure.

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?

No parameters exist and schema description coverage is 100%. Description adds no parameter info, but none is needed. Baseline score is 4 due to zero parameters.

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 clearly states verb 'Get list of' and resource 'API consents (permissions)'. Distinguishes from sibling tools like 'tochka_consent' (singular) and 'tochka_consent_create'.

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 on when to use this tool vs alternatives such as 'tochka_consent' for a single consent or 'tochka_consent_create' for creating one. Unclear context for selection.

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?

Annotations already declare readOnlyHint=true, so description adds minimal extra behavioral context. No contradiction, but no additional details about behavior beyond what annotations imply.

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?

Extremely concise: two sentences plus argument line. Front-loaded with purpose, no redundant information.

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 single-customer lookup tool with one required parameter and an output schema, the description is complete: it states the purpose, directs to sibling for listing, and documents the parameter.

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 has 0% description coverage for properties, but the description compensates by documenting the parameter with name 'customer_code', type, and an example value, adding meaning beyond the schema title.

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 verb 'get' and resource 'detailed customer information', and distinguishes from sibling 'tochka_customers' by directing the user to use that for listing codes.

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 mentions alternative tool 'tochka_customers' for listing codes, providing clear usage context. Does not explicitly state when not to use, but the purpose is clear.

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?

Annotations already provide readOnlyHint and openWorldHint, so description adds minimal behavioral info. It does mention 'accessible' which implies permission 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?

Two sentences, no wasted words, front-loaded with purpose.

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?

Output schema exists, so return values are covered. Description explains the tool's purpose and relationship to sibling. Complete for a list-only 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?

No parameters, baseline 4. Description does not need to add parameter info.

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 clearly states it gets a list of accessible customers (organizations) and distinguishes from sibling tool 'tochka_customer' which provides details on a specific customer.

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 says when to use this tool (get list) and when to use alternative ('tochka_customer' for details).

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 mentions the source of the document_id (from tochka_upd result), adding context beyond the destructiveHint annotation. However, it does not disclose permanence, side effects, or error handling. With annotations already indicating destructiveness, this is adequate but not enriched.

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, with one sentence for the action and an argument list. It front-loads the action clearly. The argument format (Args:) is non-standard but still efficient. Minimal waste, though 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 deletion tool with an output schema (not shown), the description covers the input sufficiently but omits return value or error handling (e.g., what happens if document_id is invalid). The provenance hint partially compensates for lack of broader 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 input schema has 0% description coverage, so the description fully compensates by explaining the document_id parameter as a 'Closing document UUID from tochka_upd result'. This tells the agent both the type (UUID) and the source, which is highly valuable for correct invocation.

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 deletes a closing document (UPD/Act) by document ID, specifying the verb 'delete' and the resource 'closing document'. It distinguishes from sibling delete tools like tochka_delete_invoice by explicitly naming the document type.

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 alternatives (e.g., when to delete an invoice vs. a closing document). No mention of prerequisites or conditions under which deletion 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?

The annotations include 'destructiveHint: true', which already signals destruction. The description's 'Delete' adds no further behavioral details such as irreversibility, authorization needs, or side effects. With annotations present, the description does not enhance transparency beyond the verb.

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 with only two sentences, front-loading the purpose and parameter hint. No extraneous words; every sentence adds value.

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 delete tool with one parameter, the description covers purpose and parameter origin. Annotations cover destructiveness, and an output schema exists (though not shown). No critical gaps; a user might want a note on what happens after deletion (e.g., whether it's soft or hard), but the annotations mitigate this.

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 explains that 'document_id' is an 'Invoice UUID from tochka_invoice result', which adds meaningful context beyond the schema's simple type string. This helps the agent understand the source and format of the required parameter.

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 'Delete an invoice by document ID' which specifies the verb (delete) and resource (invoice) with a specific identifier. It distinguishes from sibling tools like 'tochka_delete_closing_document' by targeting invoices.

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 delete an invoice versus alternatives like 'tochka_untrack_invoice' or 'tochka_send_invoice_email'. The description lacks context for selecting this tool over others.

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 is straightforward for a download function but does not disclose any additional behavioral traits such as file overwrite behavior or required permissions. Annotations only contain openWorldHint, which is not contradicted.

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 with no wasted words. The one-line summary is front-loaded, followed by clear parameter descriptions.

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 file download tool with an output schema, the description is sufficiently complete. It could mention potential errors or return values, but the output schema likely covers that.

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 0% description coverage, so the description adds essential meaning: document_id is the UUID from 'tochka_upd result' and output_path is an absolute path with an example. This fully compensates for the schema's lack of 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 clearly states 'Download closing document PDF to local file' with a specific verb and resource. It distinguishes from sibling tools like delete and send email.

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 usage by specifying document_id from 'tochka_upd result', indicating a prerequisite. However, it does not explicitly state when to use this tool versus alternatives like deleting or emailing the document.

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 indicates a read operation (download) with no destructive side effects, which is consistent with the openWorldHint annotation. However, it does not disclose potential limitations like file size, rewrite behavior, or network dependencies, leaving some behavioral 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?

Two sentences plus parameter lines cover everything needed. No wasted words, front-loaded with the primary action, and well-structured for quick comprehension.

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 simplicity of the tool (2 parameters, no nested objects), the description covers purpose, parameter semantics, and expected output. With an output schema available, returning to the agent is already structured, so no additional explanation is needed.

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 description coverage at 0%, the description provides crucial meaning: document_id is an invoice UUID from a specific source and output_path is an absolute file path. This fully compensates for the lack of schema descriptions.

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 downloads an invoice PDF to a local file. It distinguishes from siblings like 'tochka_delete_invoice' and 'tochka_send_invoice_email' by focusing on the download 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 description implies usage when you need a local PDF copy of an invoice and have a document_id from tochka_invoice. However, it does not explicitly state when to use this tool over alternatives, nor does it provide exclusions or when-not-to-use scenarios.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description does not need to restate that. The description adds grouping behavior and credit nature, but no additional behavioral traits beyond what annotations imply. It is consistent with annotations.

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: two sentences plus a bullet-like list of args. No wasted words. It could be slightly more structured (e.g., adding a return note), but it's efficient for the information needed.

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, the description doesn't need to detail return values. It adequately covers the input parameters, grouping behavior, and use case. It is complete for the intended purpose, though it could mention the grouping more prominently.

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 fully explain parameters. It does so clearly: month (1-12), year (e.g., 2026), inn (optional filter with example), description (optional substring filter case-insensitive). The examples and type info add significant value beyond the schema's basic type/default.

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 retrieves incoming (Credit) bank transactions grouped by debtor INN for a given month, with a specific use case for tax reports. This distinguishes it from sibling tools like 'tochka_card_transactions', 'tochka_statements_list', etc.

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 a clear use case ('useful for tax reports') and indicates the tool filters by month/year and optionally by INN/description. However, it does not explicitly mention when not to use it or compare to alternatives, though the context is adequate.

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 lacks disclosure of behavioral traits. Annotation 'openWorldHint': true suggests non-standard behavior, but no details are given about side effects, authorization requirements, rate limits, or idempotency. The tool issues an invoice (a write operation), but nothing addresses these aspects.

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 structured with an Args list, which is clear, but it is somewhat lengthy (16 lines for parameters). Some information (e.g., 'optional' labels) is redundant with the schema's 'required' list. The first sentence is concise and front-loaded, but the parameter documentation could be more 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 tool's complexity (12 parameters, 5 required), the description covers the input sufficiently but omits details on return value (beyond 'Returns documentId'), error behavior, and validation rules. With an output schema existing, it is not required to explain return values, but the description does not leverage it. It is adequate but not fully comprehensive.

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?

Despite 0% schema description coverage, the description adds significant meaning: it explains each parameter's role (e.g., 'Buyer company name', 'Total amount (calculated from positions if empty)', 'JSON array of positions...'). It also notes that 'total' can be auto-calculated. However, 'positions' is described as a JSON array but schema types it as string, causing potential confusion. Overall, it compensates well for the lack of schema descriptions.

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 'Issue an invoice to a buyer (they pay me). Returns documentId.' This provides a specific verb ('Issue') and resource ('invoice to a buyer'), and the parenthetical clarifies directionality. It distinguishes from sibling tools like 'tochka_pending_invoices' (list) and 'tochka_delete_invoice' (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 provided on when to use this tool vs alternatives. The description does not mention any prerequisites, exclusions, or comparison to related tools such as 'tochka_send_invoice_email' or 'tochka_download_invoice'. The agent must infer usage 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?

Annotations only include openWorldHint: true, indicating possible side effects. The description adds that the operation creates a payment and returns a signing URL, which clarifies the two-step nature. No contradictions.

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 well-structured: a one-line purpose, a behavioral note, and a parameter list with constraints. Every sentence adds value with no 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?

Although the output schema exists and is not described, the description covers the purpose, signing requirement, and all parameter constraints. It lacks error handling or prerequisite info, but is sufficient for a competent 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?

With 0% schema description coverage, the description compensates fully by listing all parameters with clear constraints (e.g., '10-12 digits' for INN, '9 digits' for BIC), adding significant meaning beyond the schema titles.

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 'Create outgoing payment order (I pay someone). Returns signing URL.' This uses a specific verb-resource pair and distinguishes the tool from siblings like tochka_acquiring_payment_create, which handles incoming payments.

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 mentions that 'The payment must be signed in Tochka internet bank to be processed,' providing a key usage guidance. However, it does not explicitly contrast with sibling tools or state 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?

The description is consistent with the readOnlyHint annotation, indicating a safe read operation. It adds no additional behavioral details beyond the annotations, which already cover the key traits.

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 and contains 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?

For a simple list tool with an output schema, the description provides adequate context. However, it could be more complete by explaining the concept of 'for signing' relative to other payment operations.

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?

There are no parameters, so the description does not need to add parameter meaning. schema_description_coverage is 100%, meeting the baseline for zero-parameter tools.

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 verb 'Get list' and resource 'payment orders created for signing', distinguishing it from sibling tools like 'tochka_payment' which deals with individual payments. However, it does not explicitly differentiate from similar list 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?

No guidance is provided on when to use this tool versus alternatives. Given the large number of sibling tools, usage context would help an AI agent decide appropriately.

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?

Annotations already declare readOnlyHint=true, so the agent knows it's safe. The description adds behavioral context by specifying the return format (JSON array with fields: number, buyer_inn, buyer_name, amount, description, created_at), which goes beyond annotations.

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 with four short sentences. It front-loads the main purpose, adds a usage tip, and describes output. Every sentence adds value; no wasted 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?

Despite no parameters, the description is complete. An output schema exists, and the description lists the returned fields. The tool's behavior is fully conveyed for a simple list 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?

No parameters exist, so schema coverage is 100% by default. The description adds no parameter details, but with zero parameters, the baseline is 4. It does not need to compensate for missing schema info.

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 invoices being tracked for payment. The verb 'list' and resource 'invoices being tracked for payment' are specific. It distinguishes from sibling 'tochka_check_invoices' which verifies payment status.

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 recommends using 'tochka_check_invoices' for verifying payment status, providing guidance on when to use alternative tools. No exclusions are mentioned but the context is clear.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description adds behavioral context: searching via statements and returning details for payment creation. It does not contradict annotations and adds value beyond them.

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, with one summary sentence and a bulleted args list. Every sentence adds value, and the layout is clean 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's low complexity (2 parameters, simple search), the description is complete: it covers purpose, parameters, output usage (linking to tochka_payment), and behaves as expected with annotations. No major 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?

The schema has 0% coverage for parameter descriptions, but the description explains the query parameter (INN or part of counterparty name) and days parameter (search depth in days, default 90), adding significant meaning beyond the schema's type and default.

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 it searches bank transactions by counterparty INN or name via statements, and specifies that it returns full counterparty details needed for payment creation. This distinguishes it from sibling tools like tochka_payment.

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 explains when to use this tool (to search for counterparty details) and that the output can be directly used for payment creation, implying not to use it when payment creation is needed. However, it does not explicitly mention 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?

Annotations only include openWorldHint, signaling unknown side effects. The description does not elaborate on behavioral traits such as whether sending consumes the document, requires authentication, or has rate limits. It adds minimal context beyond the argument source.

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 concise: one sentence plus two bullet-like argument explanations. It is front-loaded with the purpose. No wasted words, but could be more structured (e.g., separate sections for usage).

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 openWorldHint and the existence of an output schema, the description could be more complete. It does not explain the output, potential side effects, or prerequisites (e.g., must have a valid document). The agent may need to infer behavior from the tool name and 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?

With schema description coverage at 0%, the description adds meaning: 'Closing document UUID from tochka_upd result' and 'Recipient email address'. This provides sourcing context but lacks validation rules or examples. Baseline is adequate but not rich.

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 'Send closing document to specified email address', which is a specific verb (send) and resource (closing document). This distinguishes it from sibling tools like tochka_send_invoice_email (for invoices) and tochka_download_closing_document (download vs send).

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 on when to use this tool versus alternatives. The description hints that document_id comes from tochka_upd result, but does not explain when to prefer this over sending an invoice email or other actions. No exclusions or context 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?

The description implies a side effect (sending an email) but does not disclose idempotency, state changes, or authentication requirements. Annotations only provide openWorldHint, which adds no 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 purpose, and structured with clear parameter documentation. 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?

Adequate for a simple tool, but lacks information on response handling, error cases, or success confirmation. With an output schema existing, more context on behavior would be beneficial.

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?

Both parameters are explained with meaningful descriptions beyond the schema: document_id is 'Invoice UUID from tochka_invoice result' and email is 'Recipient email address'. This compensates for the 0% 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 clearly states the primary action 'Send invoice to specified email address'. This is specific to invoices, distinguishing it from sibling tools like tohka_send_closing_document_email.

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 on when to use this tool versus alternatives. No prerequisites or context provided, such as the need for an existing invoice or user permissions.

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?

Annotations already indicate readOnlyHint and openWorldHint. The description adds no additional behavior (e.g., pagination, ordering, recency definition). Minimal value beyond annotations.

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?

Extremely concise: two lines with purpose immediately stated. 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?

Adequate for a simple list with one parameter and an output schema, but lacks explanation of what 'statements' are, date range, or sorting. Could be more helpful.

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?

Description adds 'Maximum' to clarify limit meaning, and mentions default value. With 0% schema description coverage, this partially compensates, but is brief.

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?

Clearly states 'Get list of recent statements', identifying the action and resource. However, does not specify what kind of statements, but distinguishes from siblings since no other 'statement' tool exists.

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 on when to use this tool vs alternatives (e.g., invoices, transactions). No context on prerequisites or filtering options.

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 mentions 'recurring payment debit' but does not disclose side effects, required permissions, or consequences. With 'openWorldHint' annotation, the tool may have unstated behaviors, but the description adds no clarification. The minimal text fails to inform the agent of what happens beyond the obvious.

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 (two lines of purpose and a short argument list). It is front-loaded with the main action. However, it could be slightly more structured (e.g., using bulleted lists for clarity). Still, it achieves conciseness without being 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 complexity of a financial operation and the presence of an output schema (not shown), the description lacks details about return values, error cases, or side effects. The 'openWorldHint' annotation further suggests missing context, but the description does not fill the gaps. This is incomplete for safe agent 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?

The input schema has 0% description coverage, so the description's 'Subscription operation ID' and 'Charge amount' provide basic semantics beyond the schema titles. However, the descriptions are minimal and do not specify formats, constraints, or how the amount is applied (e.g., currency, precision). This is barely adequate.

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 explicitly states 'Charge a subscription (recurring payment debit).' The verb 'charge' and the resource 'subscription' are clear, and it distinguishes from sibling tools like 'tochka_subscription_create' or 'tochka_subscription_status' which have different actions. The 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 only says 'Charge a subscription' with no guidance on when to use this tool versus siblings like 'tochka_subscription_with_receipt' or other subscription tools. No context about prerequisites or cases where it should not be used 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?

Beyond the `openWorldHint` annotation, the description only states it creates a recurring subscription. No mention of side effects, authentication needs, rate limits, or what happens on success/failure. An incomplete behavioral picture for a write 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?

Extremely concise: a one-sentence purpose, sibling link, then a clean bullet list of parameters. No wasted words, logically 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?

The description covers the tool's purpose and all parameters. With an output schema (not shown) available, lack of return value explanation is acceptable. However, a brief example or note on success behavior would enhance completeness.

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 0% schema description coverage, the description fully compensates by providing clear explanations and constraints for all 10 parameters (e.g., '9 chars', '> 0', '1-140 chars', optionality). Every parameter is addressed.

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?

Clear verb+resource: 'Create recurring payment subscription.' Distinguishes from sibling `tochka_subscription_with_receipt` by mentioning the fiscal receipt alternative.

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 says when to use sibling tool (`tochka_subscription_with_receipt`). Provides parameter constraints (e.g., '9 chars', '> 0', '1-140 chars') but lacks broader usage context like prerequisites or conditions.

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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description adds no additional behavioral context. It correctly describes a read operation, but doesn't disclose anything beyond what annotations provide.

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: one line for purpose and a brief parameter list. No unnecessary words. Front-loaded with the main action.

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's simplicity (two optional params, output schema present), the description is adequate. It covers pagination context. Missing details about sorting or return format, but output schema likely fills 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?

Input schema has 0% description coverage, but the tool description's Args block adds clear explanations for page and per_page (e.g., 'Page number', 'Results per page'). This adds value beyond the schema's bare defaults.

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 'Get list of payment subscriptions' clearly states the verb (Get list) and resource (payment subscriptions). It distinguishes from sibling tools like create, charge, status, etc.

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 when-to-use or alternatives are provided. While the tool name and description indicate it lists subscriptions, it does not differentiate from other list tools like tochka_acquiring_payments or tochka_pending_invoices.

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?

Annotations provide readOnlyHint (true) and openWorldHint (true), which align with 'Get'. The description adds no behavioral details beyond what annotations imply, which is acceptable but minimal.

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?

Extremely concise and front-loaded. Two sentences with no unnecessary words. Every sentence serves a purpose.

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 one required parameter and an output schema, the description is sufficient but could mention that it returns status information. However, the output schema likely covers that.

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%, but the description adds 'Subscription operation ID' to the parameter, providing meaning beyond the schema's 'Operation Id' title. This clarifies the parameter's purpose.

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 'Get subscription status', which is a specific verb ('Get') and resource ('subscription status'). It distinguishes from sibling tools like 'tochka_subscriptions' (likely list) and 'tochka_subscription_status_set' (set status).

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 on when to use this tool vs alternatives (e.g., 'tochka_subscriptions' for listing all subscriptions). No mention of prerequisites or exclusions.

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 indicates a mutation ('set status', 'cancel'), consistent with the annotation `openWorldHint: true`. However, it does not disclose side effects (e.g., whether cancellation triggers notifications, refunds, or is reversible), which would be valuable given the open world hint.

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 at two sentences, front-loading the purpose. It could be slightly more structured (e.g., using bullet points for arguments), but it efficiently conveys the key information without 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 is part of a subscription management suite and has a sibling 'tochka_subscription_status' (likely for reading), the description covers the basic action and required parameters. However, it lacks prerequisites, return value details (output schema exists but not described), and behavioral context for a mutation with side effects.

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 bears full burden. It explains `operation_id` as 'Subscription operation ID' and notes `status` only allows 'Cancelled'. While helpful, it adds minimal meaning beyond the schema's `const` constraint. For a low-coverage scenario, this is adequate but not rich.

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 sets subscription status and explicitly notes it cancels the subscription. The verb 'Set' and resource 'subscription status' are clear, but it could more explicitly differentiate from sibling tools like 'tochka_subscription_status' (read-only) or 'tochka_subscription_charge'.

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 usage for cancellation but does not provide explicit guidance on when to use this tool vs alternatives like 'tochka_subscription_create' or 'tochka_subscription_charge'. It assumes the agent knows the subscription lifecycle, leaving the condition (e.g., subscription must be active) unstated.

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?

Annotations only include openWorldHint: true, meaning the tool may have dynamic behavior, but the description does not disclose any behavioral traits beyond basic operation. No mention of side effects, permissions, rate limits, or error states. The description offers minimal transparency beyond stating it creates a subscription.

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 well-structured: an opening sentence stating name and distinction, then a bullet-style list of parameters with constraints. Every item provides necessary information without 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?

Given the complexity (15 parameters, 5 required, no schema descriptions), the description covers parameters thoroughly. It mentions redirect_url and fail_redirect_url, hinting at success/failure behavior. It does not explain the output, but an output schema exists, so that's acceptable. Some further context about the overall flow (e.g., payment link generation) would enhance completeness, but it is largely adequate.

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 has 0% coverage, so the description carries the full burden of explaining parameters. It adds valuable constraints for each parameter, such as length limits for customer_code and purpose, positive amount, and optional fields with enums like tax_system_code. This greatly aids correct invocation.

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 creates a subscription with a fiscal receipt, and explicitly distinguishes from the sibling tool 'tochka_subscription_create' for subscriptions without receipts. The verb 'create' and resource 'subscription with receipt' are specific.

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 tells when to use this tool (subscription with receipt) vs. alternative (tochka_subscription_create for without receipt). Does not provide broader usage context like prerequisites or when not to use, but the sibling reference is strong 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?

The description mentions persistence ('Persists across sessions') but does not disclose other behavioral traits like idempotency, error conditions, or side effects. With no annotations, more behavioral detail would improve 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 concise: a brief statement of purpose, a sentence on persistence, guidance on related tools, and clear parameter list. 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's complexity (6 parameters, 5 required) and presence of an output schema, the description is fairly complete. It explains purpose, persistence, parameter meanings, and links to related tools. Minor gaps: no mention of prerequisites or return behavior.

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?

Despite 0% schema description coverage, the description adds substantial meaning to each parameter with examples (e.g., 'number: Invoice number (e.g. "140")') and clear explanations (e.g., 'buyer_inn: Buyer INN (who should pay)').

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's purpose: 'Start tracking an invoice for payment.' It distinguishes itself from siblings like 'tochka_pending_invoices' (list tracked) and 'tochka_check_invoices' (check payments).

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 guidance on when to use this tool vs. siblings: 'Use tochka_pending_invoices to list tracked invoices, tochka_check_invoices to check payments.' However, it does not cover all alternatives or when not to use this tool.

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?

Annotations already include destructiveHint: true, indicating modification. Description adds no extra behavioral details (e.g., irreversibility, side effects). With annotation cover, this is adequate but not enhanced.

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?

Extremely concise, two sentences only. No filler, front-loaded with core purpose.

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?

Tool is simple with one parameter and output schema exists. Description covers essential usage but could mention reversibility or what happens to the invoice after untracking. Still, sufficient for a straightforward undo 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 has 0% coverage; description compensates by explaining that 'number' is the invoice number from specific sources, adding meaningful context beyond the schema's type definition.

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?

Clearly states 'Stop tracking an invoice by its number' – verb and resource are specific. Distinguishes from sibling tools like tochka_track_invoice and tochka_delete_invoice.

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 source for the invoice number (from tochka_track_invoice or tochka_pending_invoices), guiding the agent on where to obtain it. Does not explicitly exclude alternative scenarios, but the context is sufficient for a simple untrack operation.

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?

Annotations only include openWorldHint: true. The description adds that the tool returns documentId and signURL and defaults to 'schfdop' function, but does not disclose side effects, permissions, or error behaviors. It does not contradict annotations.

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 structured with a clear purpose statement followed by an argument list. It is somewhat lengthy but efficient, front-loading the key purpose. Minor redundancy ('same format as invoice') could be trimmed but overall well-organized.

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 12 parameters, 5 required, and an output schema exists (so return values are covered), the description explains all parameters and the return value. It is complete for a UPD creation tool, though could elaborate on validation or constraints.

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%, meaning the description provides the sole parameter explanations. The description lists each parameter with a brief but meaningful explanation (e.g., 'buyer_type: company or ip' and 'function: schfdop (invoice+primary) or dop (primary only)'), adding critical 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 clearly states it creates UPD (universal transfer document) and returns documentId and signURL. It specifies the default function ('schfdop') and distinguishes this tool from other document-related siblings by focusing on UPD creation.

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 explains the default and optional parameters but does not explicitly state when to use this tool vs alternatives. No when-not scenarios or prerequisites are mentioned, leaving the agent to infer usage context.

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