Vérifier ma facture (Factur-X)

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds content details (the grid's scope and normative references) but does not describe behavioral nuances such as whether the list is static or dynamically generated, or the return structure. No contradiction 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 exactly two sentences: the first states what the tool returns, and the second states its utility. Every phrase contributes value without redundancy or 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 zero-parameter listing tool with no output schema, the description fully covers the return content (complete grid, criteria categories, normative references) and practical applications. It is self-contained, allowing an agent to understand when and why to invoke it.

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 the schema is empty with 100% coverage. Per the baseline for zero parameters, the description does not need to explain parameters. It adds no parameter-specific information, which is appropriate and consistent with 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 uses the specific verb 'Rend' (returns) with a clear resource: the complete grid of Factur-X compliance criteria checked by verifier_facture. It distinguishes itself from the sibling by referencing verifier_facture's checks and enumerating content categories (essential, strict, advanced) and normative references.

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 provides explicit practical use cases: 'Utile pour expliquer un rapport ou préparer une facture conforme' (useful for explaining a report or preparing a compliant invoice). This implies when to use the tool, though it does not explicitly state when not to use it or contrast with verifier_facture beyond naming 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 annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable behavioral context: 'L'analyse est locale et éphémère : la facture n'est ni stockée ni transmise à un tiers.' It also describes the report's structure (essentiels, stricts, avancés), going 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 three sentences, all information-dense: purpose, criteria breakdown, input requirement, and privacy guarantee. No filler or repetition, properly 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?

There is no output schema, but the description outlines what the report contains (21 criteria across three categories) and covers input constraints and privacy. The sibling tool lister_criteres likely provides the full criteria list, making this description sufficiently complete for an agent to decide and invoke.

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 both parameters described, so the baseline is 3. The description adds a key constraint (10 Mo maximum) and reinforces the base64 encoding format, providing additional semantic value 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 a specific action ('Analyse un PDF de facture et rend un rapport de conformité Factur-X') and a concrete deliverable (21 criteria across three categories). This distinguishes it from the sibling tool lister_criteres, which likely only lists criteria rather than verifying a PDF.

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 explicit prerequisites: 'Fournir le PDF encodé en base64 (10 Mo maximum)' and mentions the input format. However, it does not explicitly contrast with the sibling tool lister_criteres or say when not to use this tool, though the purpose implies it for PDF verification.

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