Mes Frais de Notaire

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

No annotations were provided, so the description carries the full burden of disclosing behavior. The verb 'Estime' implies a read-only calculation, but the description does not explicitly state it has no side effects, requires no authentication, or always succeeds under the given parameters. It also does not mention what the agent should expect regarding response format or whether it is a pure function of the inputs. For a no-annotation tool, this is a notable gap.

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 one compact sentence that front-loads the return value and its components. The 'Même logique que le site et GET /api/calculate' clause is a light anchor for consistency, though it is not strictly necessary. There is no wasted wording, making it well structured.

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 there is no output schema, the description partially covers the return value by naming the fee components, but it does not describe the exact response shape or whether the total is also itemized. It also fails to mention how department-specific rates are handled or when to use compare_departements/get_departement_info. For a 6-parameter financial calculator, an agent would benefit from one more sentence about outputs and conditions.

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 all six parameters already have clear descriptions; the baseline is 3. The description adds only a rough mapping to inputs ('prix, département, type de bien, profil') and lists the fee components, which is helpful but not substantially better than the schema. It does not clarify the exact meaning of 'profil' beyond what the 'primo' parameter describes.

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 ('Estime') and resource ('les frais de notaire'), naming the underlying components (DMTO, émoluments, CSI, débours). It is clearly distinct from siblings like compare_departements and get_departement_info, though it does not explicitly name them. It would be a 5 if it explicitly identified when to choose this tool over a sibling.

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 the tool is used when estimating notary fees from price, department, property type, and profile, but it gives no explicit guidance on when not to use it or when to prefer a sibling. The reference to 'Même logique que le site et GET /api/calculate' hints at a mirror of another endpoint but does not provide decision criteria. This is adequate context, but it leaves the alternative-selection reasoning to the agent.

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?

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.

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

No annotations are supplied, so the description alone must disclose behavioral traits. It only mentions the output content and never states that the operation is read-only, how invalid codes are handled, what response format is used, or any other operational side effects (e.g., rate limits or prerequisites). The lack of this information is a meaningful gap for an agent invoking the tool.

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 one short, front-loaded sentence that communicates the tool's purpose and the full list of return fields without any filler. Every item in the list is relevant and the structure directly supports agent comprehension.

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 single-parameter read-only lookup with no output schema or nested objects, the description is largely complete because it lists exactly what the agent will receive. It falls short only in not describing error behavior for invalid department codes or the concrete JSON response shape, but it covers the main informational needs for correct invocation.

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 input schema already documents the single parameter 'code' with its type and example values, achieving 100% schema coverage. The description adds context about DMTO rates and the domain, but it does not enrich the meaning of the 'code' parameter itself, so the baseline for full schema coverage 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 opens with 'Retourne' (returns) and lists the exact data fields: nom, région, préfecture, taux DMTO standard/appliqué, hausse 2025, slug. This makes the tool's purpose unmistakable and distinct from siblings calculate_frais_notaire and compare_departements, which involve calculation and comparison rather than simple information retrieval.

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 the tool is used to fetch static department metadata by the list of returned fields, but it does not explicitly state when to prefer it over the sibling tools or when not to use it. No exclusions or alternative routing are provided, so the agent must infer usage from the name and output fields.

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