company-data

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

Annotations already provide readOnlyHint and openWorldHint. The description adds useful context: yearly history, specific fields, and amounts in RON. 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?

Single sentence with all crucial information front-loaded. 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 2-param tool with no output schema, the description is minimal but covers core data. Lacks explicit parameter guidance and return structure details, making it adequate but not 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?

With 0% schema description coverage, the description should explain parameters. It mentions 'by CUI' hinting at the cui parameter, and 'yearly' hints at years, but does not explicitly define years or its constraints. Inadequate for compensating missing schema documentation.

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

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

The description clearly states it returns yearly financial history for a company by CUI, listing specific fields (revenue, profit, etc.) and currency. This distinguishes it from siblings like get_company_profile (profile data) or get_company_status (current 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 implies usage for retrieving financial history, but does not explicitly state when to use or avoid, nor does it mention alternatives among siblings. The usage context is only implied.

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 read-only, non-destructive. Description adds that it does not return contact details and mentions data-source freshness, providing extra behavioral context 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 clear sentences with no extraneous information. Front-loaded with main action and input 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?

For a simple fetch tool with one parameter and no output schema, description covers return data fields, limitations (no contact details), and data freshness. Meets 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?

Schema coverage is 0%, but the description adds essential semantic info for the only parameter 'cui' by noting it accepts an 'RO' prefix, which is not in 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?

Description clearly states verb 'Fetch', resource 'Romanian company', input 'CUI', and lists returned data fields. It distinguishes from siblings by explicitly noting what is not returned (contact details).

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?

Description implies usage context but does not specify when not to use or provide comparisons to sibling tools beyond the list. No explicit exclusions or alternatives.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description is not required to restate safety. It adds value by listing the specific data points returned (e.g., insolvency, dissolution), providing concrete behavioral insight 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, well-structured sentence that front-loads the purpose and lists the flags efficiently. 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 lookup tool with one parameter and no output schema, the description sufficiently covers what the tool returns. It lists all relevant status flags, and no additional context (e.g., pagination) 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?

Schema description coverage is 0%, so the description must clarify the parameter. It mentions 'by CUI' but does not define CUI or explain its format. For a single required parameter, minimal explanation is acceptable but could be more explicit, e.g., 'Romanian company tax ID'.

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 company status' and specifies the resource: status flags by CUI. It lists the exact flags included (registration, VAT, fiscal activity, insolvency, dissolution, e-Factura), distinguishing it from sibling tools like financials or profile.

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 when to use (when you need company status flags), but does not explicitly state when not to use it or compare to alternatives. No exclusion criteria or context for choosing over siblings like get_company_financials or search_companies.

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 and destructiveHint=false, so safety is clear. The description adds behavioral context: the tool returns the official label and hierarchy. There is no contradiction. With annotations present, the description 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?

Two sentences with no wasted words. The first sentence front-loads the purpose and output, the second adds detail about language. Each sentence earns its place.

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

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

The tool has one parameter and no output schema. The description adequately covers input (the code to look up) and output (official label and hierarchy), along with the language context. No missing essential information.

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 explains that the 'code' parameter is a Romanian CAEN (NACE) activity code, which adds meaning beyond the schema's type and length constraints. It also describes the output.

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', resource 'Romanian CAEN (NACE) activity code', and output 'official label plus hierarchy (section, division, parent)'. It also notes that labels are in Romanian. This distinguishes it from sibling tools which focus on company data.

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 indicates when to use this tool (to look up a CAEN code) but does not provide explicit when-not or alternative guidance. The sibling tools context shows different purposes, so usage 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?

The description adds value beyond annotations by disclosing that it returns up to 25 results per page with an opaque cursor, financial filters use a single year (default 2024), and at least one filter is required. These details help the agent anticipate pagination and filtering behavior. It does not contradict annotations (readOnlyHint, openWorldHint, destructiveHint).

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 with no redundancy. It front-loads the core purpose and then adds essential details (pagination, year default, filter requirement). Every sentence adds unique value without being 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 (15 parameters, no output schema), the description adequately covers filtering capabilities, pagination, and a default year. It does not explain the output format or fields, which would be helpful. However, for a search tool with optional filters, it provides sufficient context for basic 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?

With 0% schema description coverage across 15 parameters, the description partially compensates by grouping parameter types (e.g., name, CAEN activity, county/locality, revenue/profit/employee ranges, VAT status). However, it does not explain individual parameters like cursor, active_only, or the exact meaning of min/max ranges, leaving some ambiguity.

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 and filters a company directory by multiple criteria, and it distinguishes from sibling tools (which are for specific lookups like profile or financials). The verb 'Search and filter' and the specific resource 'Firme Românești company directory' make 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 provides clear context: it is a search tool with pagination (opaque cursor), default year, and the requirement to provide at least one filter. It implicitly distinguishes from sibling tools (e.g., get_company_financials for financial details), but it does not explicitly state when to use this tool over 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.