api

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description doesn't need to add safety behavioral traits. It provides the identifier format and expand usage, which adds some value but no additional behavioral constraints (e.g., rate limits, authentication needs, or side effects). The description is adequate but not enriching beyond what annotations convey.

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 two concise sentences. The first sentence captures the core purpose and key parameter, and the second adds a valuable usage tip. No unnecessary words or redundancy. Front-loaded with the most critical 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 straightforward fetch tool with no output schema and three well-documented parameters, the description covers the input side well. It lacks an explicit statement about what is returned (e.g., the full company object), but given the simplicity and the context from sibling tools, an agent can infer the output. Completeness is strong but not perfect due to the missing return description.

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 100% and each parameter already has a detailed description. The tool description merely rephrases the 'expand' parameter's purpose ('use expand to include related data in one call') without adding new semantics. Since the schema does the heavy lifting, a baseline of 3 is appropriate.

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

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

The description clearly states the action ('Fetch one company'), the resource ('company'), and the required identifier ('DatoCapital company id (uec)'). It also highlights an optional capability ('expand to include related data'). This is specific and distinct from sibling tools like get_company_filings or search_companies.

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 (when you have a specific company id) and provides context that the id comes from search_companies or resolve_company_number. However, it does not explicitly state when not to use it or compare to alternative tools, leaving some ambiguity for the agent.

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 operation) and openWorldHint=false. The description adds that results are sorted newest first by default, which is useful behavioral info beyond annotations. However, it does not disclose pagination behavior (beyond the cursor and page_size parameters) or rate limits.

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

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

The description is a single sentence that efficiently conveys the core purpose, examples of content, and default sort order. There is no redundancy or unnecessary text.

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

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

Given the tool has 9 parameters but no output schema, the description covers the core purpose and default sorting. The absence of output schema details is acceptable because the tool likely returns a list of filings with well-understood fields. The description is complete enough for an experienced user.

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

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

Schema description coverage is 100%, so the schema already documents all parameters well. The description mentions 'one company' implying the uec parameter, and 'newest first' hinting at sorting, but does not add substantial meaning beyond what the schema provides. A baseline score of 3 is appropriate.

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

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

The description clearly states the tool lists filings for a specific company and gives examples of filing types (registry acts, financial statements, gazette notices) and default sorting order (newest first). It distinguishes the tool from siblings like get_company and search_companies by focusing on filings.

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

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

The description implies this tool is used to retrieve filings for a single company, but it does not explicitly state when to use it versus alternative tools like search_companies (which might search across companies) or get_company (which retrieves company profile data). It does not mention any prerequisites or limitations.

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 doesn't need to emphasize idempotency. The description adds valuable behavioral context: it indicates the output includes 'delivery mode and price information' (not just availability), it names the data source (DatoCapital), and implies the tool returns a scope of items rather than a single detail. This goes 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 remarkably concise: a single sentence that packs the resource ('commercial reports and certificates'), scope ('one company'), provider ('DatoCapital'), and output highlights ('delivery mode and price'). No wasted words, all information front-loaded and actionable.

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 (2 parameters, no output schema, no nested objects, no enums), the description is largely complete. It explains what the tool returns and the scope. A minor gap is that it doesn't mention whether results are paginated or if there's a limit on report types, but for a non-paginated listing tool this is adequate. The description covers the essential completeness needs.

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

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

The input schema already provides 100% coverage via its property descriptions (clear descriptions for 'uec' as company id and 'language' with example values). The description does not add new parameter-level meaning, but the overall description of what the tool returns compensates slightly by providing context for understanding the parameters' purpose. Baseline 3 is appropriate given full 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 tool's purpose with a specific verb ('Show') and direct object ('commercial reports and certificates'), names the data provider (DatoCapital), clarifies the scope ('for one company'), and hints at what the result contains ('delivery mode and price'). This distinguishes it from sibling tools like get_company or get_company_filings which have different resources.

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

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

The description gives clear context for what the tool does ('which commercial reports and certificates...can deliver'), which implies it's a lookup/preview tool. However, it provides no explicit guidance on when to use this versus alternatives like get_company_filings or search_companies, and does not state when to avoid using 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 already declare readOnlyHint=true, so the read-only behavior is clear. The description adds behavioral context by explaining the effect of the expand parameter ('to include the roles this person holds across companies'). This goes beyond the schema's simple 'Allowed: positions' and helps the agent understand the expanded output.

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 with no unnecessary words. The first sentence gives the core purpose, and the second provides a specific usage tip. Every word earns its place, and the description is front-loaded with the essential 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 (fetch by ID, no output schema), the description is mostly complete. It covers the primary action and a key optional parameter. However, with no output schema, a brief note on the return structure (e.g., 'returns a person object') would improve completeness. Still, it is adequate for a straightforward fetch operation.

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

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

Schema coverage is 100%, so the schema already provides baseline descriptions. The description adds value for the 'expand' parameter by stating its purpose ('include the roles this person holds across companies'), which clarifies its semantics beyond the schema. The 'id' and 'language' parameters are already well-described in the schema, and the description does not add to them.

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 'Fetch one individual by DatoCapital person id,' specifying a single verb (fetch) and resource (individual). It distinguishes from sibling tools like search_individuals (which returns multiple) and other entity-specific tools like get_company.

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 have a specific person id and need an individual record, and it hints at the expand parameter for roles. However, it does not explicitly state when to prefer this over alternatives like search_individuals or what not to use it for. Usage context is implied but not fully articulated.

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, indicating a safe read operation. The description adds the detail about native-language names, which is a minor behavioral trait. However, it does not disclose any other behavioral aspects (e.g., whether the list is sorted, cached, or limited). The description adds limited value beyond the 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 a single sentence that is direct and front-loaded with the core action. Every word serves a purpose, with no unnecessary elaboration.

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

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

Given the tool has no parameters, no output schema, and is a simple list operation, the description is complete. It specifies what is listed (countries with data) and an additional detail (native-language names). No further information is needed for an agent to correctly invoke this 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?

The tool has zero parameters, and schema description coverage is 100% (trivially). The description does not need to add parameter semantics. With no parameters, a baseline of 4 is appropriate, as the description is not required to compensate for missing parameter documentation.

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

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

The description clearly states the verb 'list' and the resource 'countries', and specifies the scope 'DatoCapital has company data for' with the detail 'with native-language names'. This distinguishes it from sibling tools which focus on companies, filings, individuals, 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 implies the tool is for retrieving the list of countries with available data, but it does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. The simplicity of the tool (no parameters) reduces the need for extensive guidance, but some contextual hints would improve clarity.

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 does not need to reiterate safety. The description adds that the tool normalizes and splits legal forms, but it does not disclose return format, error behavior, or any additional traits. With annotations covering the baseline, this adds moderate 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, front-loaded with the core action and output, followed by a concise guideline on the country parameter. No redundant or vague language.

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 no output schema, the description explains the purpose and a key parameter hint. However, it does not specify the return structure (e.g., whether it returns a single string or a JSON object), which would be beneficial for an agent. Adequate but not fully complete.

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

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

Schema coverage is 100% with clear descriptions. The description adds value by explaining why the country parameter matters ('country-specific legal-form detection'), which goes beyond the schema's bare enumeration. This helps the agent decide whether to provide the optional 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 the verb 'clean' and the resource 'free-text company name', and specifies the outputs: detect and split legal form, return normalized name. It distinguishes this normalization tool from all sibling tools (search, get, list, etc.), leaving no ambiguity.

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

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

The description implies usage by saying 'Give a country for country-specific legal-form detection', but it does not explicitly state when to use this tool versus alternatives, nor does it mention when not to use it. No exclusions or alternative tool references are provided.

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

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

Annotations already provide readOnlyHint=true and openWorldHint=false. The description adds the behavioral context of being a 'direct' lookup by registry number, but does not elaborate on what happens if the company number is not found, any permissions needed, or rate limits. With good annotation coverage, the description adds modest 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?

The description is extremely concise: two front-loaded sentences with zero filler. Every word adds value – first sentence states the action and parameters, second sentence provides the usage condition.

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

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

For a simple two-parameter lookup tool with no output schema, the description is minimally adequate. It lacks any explanation of what the tool returns (e.g., full company details vs. just resolution status) and does not address edge cases like missing registrations. Given the existence of sibling 'get_company', more context on output would be 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?

Schema description coverage is 100% – both parameters have clear descriptions (country format with examples, company_number with example). The tool description does not add any additional parameter semantics beyond what the schema already provides, so baseline score of 3 is appropriate.

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

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

The description clearly states the verb 'Look up' and the resource 'one company directly by country and national company number'. It distinguishes from siblings like 'search_companies' and 'normalize_company_name' by specifying that this is a direct lookup using an official registry number.

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 includes the usage condition: 'Use this when you already know the official registry number.' This clearly tells the agent when to invoke this tool and implicitly indicates when not to (e.g., when only a company name is known), guiding toward alternative sibling tools.

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

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

Annotations already declare readOnlyHint=true, so no mutation. The description adds behavioral details: returns a page of companies, uses opaque cursors for pagination, and supports direct lookup with specific parameters. This goes beyond the annotations but is not exhaustive; for instance, no mention of response structure or potential errors, hence a 4.

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 front-load the core purpose, then add specific pagination and direct lookup behavior. Every sentence adds necessary context with no filler, achieving optimal efficiency.

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

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

Given 10 parameters and no output schema, the description is essential but not fully complete. It explains pagination and the direct lookup pattern, yet it omits details about the response format, default sort order, or how results are structured. This is adequate for a search tool but leaves gaps for an agent needing full 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?

Schema coverage is 100%, so descriptions in schema are thorough. The tool description adds valuable semantic guidance for combining cif and country for direct lookups, which enhances understanding beyond individual parameter descriptions. Not all parameters get extra treatment, but the combinatorial hint justifies a 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?

The description clearly states 'Search legal entities by free text and structured filters,' specifying the verb and resource. It further distinguishes from sibling tools like get_company by mentioning pagination with opaque cursors and a direct lookup capability with cif+country, making the tool's unique purpose unmistakable.

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 concrete usage tip: 'Give cif together with country for a direct registry-number lookup,' which guides effective parameter combination. However, it lacks explicit guidance on when to prefer this tool over alternatives (e.g., get_company) or when not to use it, so it falls short of a 5.

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 annotation 'readOnlyHint: true' already informs the agent this is a read-only operation. The description adds useful context about searching individuals with a corporate affiliation. However, it does not disclose any additional behavioral traits such as pagination behavior (beyond what the cursor parameter suggests), result ordering, or rate limits. Since the description does not contradict annotations and adds some value, a score of 3 is appropriate.

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, clear, and concise sentence. Every word serves a purpose: it specifies the resource ('natural persons'), the context ('who hold or held positions in companies'), and provides an example ('such as directors and officers'). No fluff or repetition. For a search tool with many parameters, this is optimally brief and front-loaded.

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

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

Given the tool has a read-only annotation, a full schema with 100% coverage, and no output schema, the description completes the picture by clarifying the scope (individuals with corporate roles). For a search tool, it lacks a hint about the default sort order or result format, which would be helpful but is not critical. The description is complete enough for an agent to use the tool correctly in most cases.

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 100%, so the schema already documents all 7 parameters well. The description provides high-level context ('Search natural persons who hold or held positions in companies, such as directors and officers.') that frames how parameters like 'position_kind' and 'country' should be used. However, it does not elaborate on parameter syntax (e.g., date formatting for 'dob_year') or defaults beyond what the schema provides. The description adds a conceptual layer, earning a 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?

The description clearly specifies the verb ('search') and the resource ('natural persons who hold or held positions in companies, such as directors and officers'). The examples ('directors and officers') and the 'positions in companies' phrase effectively distinguish this tool from siblings like 'search_companies' (which searches for organizations) and 'get_individual' (which retrieves a specific individual). The purpose is precise and 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 implies this tool is for searching individuals with roles in companies, which helps the agent choose between it and 'search_companies' or 'get_individual'. However, it does not explicitly state when NOT to use it (e.g., for general people searches without a corporate role) or provide specific alternatives beyond the sibling list. The context is clear but lacks explicit 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 annotations already declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a safe read operation. The description adds 'Fast' as a performance trait and 'before a full search' as usage context, but it does not disclose details about result ranking, pagination, or limitations. With annotations covering safety, some additional behavior could be shared, but the current level is adequate.

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 two short sentences with no redundant information. The key action (autocomplete) and the use case are front-loaded, making it easy for an agent to parse quickly.

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, the schema's full parameter documentation, and the read-only annotation, the description provides sufficient context for an agent to select and invoke it. No output schema exists, but the return value is implied by 'autocomplete' (a list of suggestions). The description covers the purpose and placement in the workflow, so it is complete enough.

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

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

The schema provides 100% coverage of all four parameters, including descriptions for q, kind, country, and max_results. The description only restates the overall purpose (autocomplete names) without adding new semantic details about parameters, so it does not exceed the baseline score of 3.

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

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

The description clearly states the tool's function: 'Fast autocomplete for company or individual names.' It uses a specific verb (autocomplete) and resource (names), and distinguishes itself from sibling search tools by specifying its role: 'Use it to resolve a partial name before a full search.'

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

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

The description provides clear usage context: it should be used to resolve partial names before performing a full search. This implies the tool is for exploratory/autocomplete purposes rather than exact lookups. However, it does not explicitly name alternative tools such as search_companies or search_individuals, nor does it say when not to use it.

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

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

Annotations already declare readOnlyHint=true, establishing it as a safe read. The description adds behavioral context by specifying the scope (account, plan information) and the purpose (credential verification). This effectively complements the annotation without 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?

The description uses two tight sentences, each earning its place: the first states what it shows, the second tells when to use it. No wasted words, and the key information is front-loaded.

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

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

For a zero-parameter tool with annotations and no output schema, the description provides a complete picture: it tells what it does, why to use it, and that it returns account/plan info. It could optionally hint at the output structure, but given the simplicity, this is 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 tool has zero parameters, so the baseline is 4 per the evaluation rubric. The description adds no parameter detail because none are 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?

The description clearly states that this tool 'Show[s] the account behind the API key in use', which is a specific verb+resource pair. It distinguishes itself from all sibling tools (none deal with current identity), making the purpose 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 explicitly tells the agent to 'Use it to verify credentials', providing a concrete use case. While no alternatives are named, there are no sibling tools that serve a similar function, so the guidance is sufficient.

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