Créer une référence (expérience pro) sur une ressource

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

Critically, the description discloses the read-modify-write behavior: it reads the current list via /resources/{id}/technical-data, appends the new reference, and republishes the complete list. This is a non-obvious side effect (potential overwrite/lost update risk) that an agent must know. It also mentions the API quirk that the created reference's ID is not returned directly and must be extracted from the response. All of this adds significant value beyond the annotations (which only say the tool is not read-only).

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 fairly concise and front-loaded with the core purpose. It uses short paragraphs and bullet points effectively. It loses one point because the warning about leading zeros is repeated twice for startMonth/endMonth, and the mention 'Plutôt que: boond_resources_technical_data_update' is slightly confusingly phrased. Otherwise, every sentence contributes value.

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 complexity (read-modify-write, embedded sub-object, API quirk), the description covers the essential aspects: required fields, date format pitfalls, return value behavior, and sibling differentiation. However, it does not mention potential failure modes (e.g., what happens if the resource does not exist, or how to handle concurrent modifications). For a create operation on an embedded resource with no output schema, this is a minor gap.

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 descriptions for each parameter, so the baseline is 3. The description adds semantic meaning by grouping required fields (resourceId, title, company, description) and by warning about the leading-zero rejection for month fields ('05' rejected) and the int format (year as 4 digits, month as 1-12). It also explains that 'skills' is a comma-separated listaine. This compensates for the schema's terse descriptions and adds format constraints not present 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 states a specific verb ('Crée') and a specific resource ('expérience professionnelle (référence) sur une ressource'), identifying it as a sub-resource of the technical data. It clearly distinguishes from siblings by naming boond_resources_reference_update and boond_resources_technical_data_update, clarifying that this tool does not touch other technical data blocks.

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?

Explicitly explains when to use this tool (create a new reference) and when NOT to (to complete an existing reference, use boond_resources_reference_update to avoid duplication). It also mentions that boond_resources_technical_data_update should not be used for other technical data blocks via this tool. This is clear, actionable guidance.

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