auregistre

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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses key non-obvious behaviors: filtering by publication date rather than act date, the median 16-day discrepancy, the rate limit cost per company, and the meaning of an empty list. This is exactly the kind of behavioral context an agent needs.

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-ordered: it states the core purpose, then the operational constraint, then the subtle date-filter caveat. Every sentence earns its place with no fluff or repetition of the schema.

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

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

For a two-parameter read-only tool, the description covers purpose, query intent, batching, and empty-result semantics. It does not describe the response fields or pagination, but the absence of an output schema is mitigated by the simple, familiar 'list of announcements' mental model.

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

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

The schema already documents both parameters fully, including SIREN formatting and the since default, so the baseline is 3. The description adds extra value by clarifying that 'since' refers to publication date and by explaining the per-company rate-limit consumption, which affects batching.

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: retrieving French official gazette announcements about companies since a date. It uses concrete user questions to make the resource and scope obvious, and it is distinguishable from siblings like financials or timeline by its 'announcements in the gazette' focus.

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?

It gives strong usage guidance for the 'any news since my last check' scenario and explicitly instructs users to batch up to 20 companies in one call. It does not explicitly contrast itself with sibling tools, but the purpose and context are clear enough for correct 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?

Beyond the readOnly/openWorld/idempotent annotations, the description discloses critical behavioral quirks: legal-entity and consolidated group accounts are listed apart and never add up, confidential filings are omitted, missing fiscal years are not zeros, and amounts are in euros as filed. This is exactly the kind of context an agent needs to avoid misinterpreting results.

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 front-loaded with the resource and data items, then usage examples, then essential caveats. Every sentence adds distinct value: content, use cases, accounting perimeter nuance, confidentiality/missing data behavior, and units. No filler or redundancy.

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

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

For a read-only financial data tool with no output schema, the description is remarkably complete: it names the available metrics, the entity scope, the units, the meaning of missing data, and the critical consolidation caveat. An agent has enough context to select, invoke, and interpret results correctly.

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

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

Schema description coverage is 100% and the single parameter 'siren' is already well-documented with pattern and SIRET-to-SIREN conversion guidance. The description adds contextual meaning by tying the data to 'this SIREN' and the legal entity perimeter, but the schema already carries the load, so a baseline 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 starts with a specific verb+resource: 'The annual accounts one French company filed with the business register, fiscal year by fiscal year' and enumerates exact fields (revenue, gross margin, EBITDA, EBIT, net income, thirteen ratios). It clearly distinguishes this tool from siblings focused on announcements, timeline, and insolvency by specifying financial accounts content.

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 'Use this to answer' questions about revenue, profitability, turnover evolution, and indebtedness, which is clear when-to-use guidance. It does not explicitly name sibling alternatives or state when not to use it, but the use-case framing is strong enough to guide 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?

Beyond the strong annotations, the description adds valuable behavioral context: coverage starts at 2008, a company may exist without any published changes, unchanged fields are absent, and SIREN-only announcements are excluded with an approximate noise rate. This materially sets agent expectations.

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?

Every sentence earns its place: purpose, usage guidance, exclusions, coverage limitation, and data relevance. It is longer than average but all content is decision-relevant for an agent, and the structure front-loads the core definition.

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

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

The description is very complete for selecting and invoking the tool: it lists the returned change types, boundaries, and failure-relevant coverage limits. It stops short of describing the exact response shape or ordering, but with no output schema, the field list and change semantics give enough context for correct 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 100%, so the schema already fully documents the single 'siren' parameter, including format and the SIRET distinction. The description adds no new parameter-level semantics, so the 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 states an extremely specific scope: every dated change recorded in the French official gazette for one company, with explicit fields (share capital, legal name, legal form, registered office, stated activity, insolvency judgments). It clearly distinguishes itself from current-state tools by emphasizing that only changes are published.

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 explicit example questions to answer and directly says 'Do NOT use it to get the current state', which is excellent negative guidance. It does not name sibling tools as alternatives, so the routing is not quite as explicit as it could be, but the use cases and exclusions are 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?

Beyond the annotations, the description discloses critical behavioral traits: it counts 'OPENING judgments only' and 'judgments, not companies,' and explains that the current month is excluded because it would 'read as a collapse.' These quirks would not be inferable from the schema or annotations alone.

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 efficiently organized: the core metric and comparison period in the first sentence, scope in the second line, and key caveats in the final paragraph. Every sentence adds necessary information without repetition or 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?

Given the two optional enum parameters and the presence of an output schema, the description is complete. It specifies the time window, the counting unit, the exclusion of the current month, the nature split, and the filtering rules. An agent has everything needed to invoke the tool correctly.

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

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

Schema description coverage is 100%, so both parameters are already documented with enums and descriptions. The description adds value by clarifying that department and trade are mutually exclusive scope filters and that omitting both gives the whole country, which is not fully explicit 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?

The description opens with a specific verb and resource: 'Insolvency openings in France over the last twelve complete months, against the twelve before.' It clearly distinguishes this tool from the sibling company-focused tools by stating exactly what data it returns and its scope options.

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 when to use the tool: default whole country, or one department, or one trade, and explicitly says 'Pass at most one of them.' It does not explicitly name sibling tools or state when not to use them, but the scope guidance is strong enough for an agent to select it correctly.

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