validate_invoice

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

With no annotations, the description carries the full burden. It mentions 'irréversible' (irreversible), which is a key behavioral trait, but the phrase is incomplete ('sans avoir') and lacks context. It does not disclose side effects like stock movements via idwarehouse, permissions, or post-validation status changes, leaving significant gaps in behavioral understanding.

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 brief, which is generally good, but it is truncated and grammatically incomplete ('sans avoir'). This undermines clarity and makes it seem unpolished. A complete sentence would be more effective.

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 performs a critical state transition with potential side effects (e.g., stock movements via idwarehouse), yet the description is minimal and does not explain the process, consequences, or return values. Without an output schema and with no annotations, more detail is needed for an agent to use it 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% with both parameters described. The description adds no parameter-level detail beyond what the schema already provides, so it meets the baseline for high schema coverage. No additional syntactical or semantic clarification is offered.

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 identifies the tool as validating a draft invoice to make it official, using a specific verb and resource. It distinguishes from other validate_* siblings by specifying 'facture brouillon' (draft invoice). However, the phrase ends ambiguously with 'sans avoir' (without having), which slightly obscures the intended meaning.

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 like validate_order or validate_proposal. The purpose is implied, but there are no stated conditions, prerequisites, or exclusions. Sibling tools with similar validate_* patterns are present, but the description does not address selection criteria.

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