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

With no annotations, the description carries the full burden and does disclose the main outputs and the 'non primo' qualifier. However, it omits output format, error handling, and any side-effect details; since this appears to be a read-only comparison, the lack of mutation warnings is less critical.

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 short and front-loaded with the purpose and output. The final 'Maximum 25 codes' is redundant with the schema's maxItems, but this is a minor inefficiency in an otherwise compact 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 covers input, output, and a constraint, but with no output schema and no annotations it leaves the response structure and error behavior unspecified. Sibling differentiation is also absent, so an agent has enough to call it but not 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%: the schema already describes 'codes' as department codes and enforces maxItems 25. The description repeats the list context and maximum, adding no meaningful parameter-level semantics beyond what the schema provides, so the baseline 3 applies.

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 a specific verb ('retourne') and names the exact resource (taux appliqué non primo, indicateur de hausse 2025), making the tool's function clear. It does not explicitly differentiate from siblings, but the DMTO-rate focus distinguishes it from calculate_frais_notaire and get_departement_info.

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 guidance is given about when to choose this tool over its siblings or when not to use it. The phrase 'Pour une liste de codes département' only describes the input context, not the decision boundary between compare_departements and calculate_frais_notaire or get_departement_info.

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