Relance des CRA du mois

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description goes further: 'N'appelle aucune API BoondManager et ne lit aucune donnée : la réponse est générée côté serveur MCP.' It also clarifies the return behavior: 'Returns : un runbook en texte — la liste ordonnée des appels Boond à effectuer, avec les filtres exacts. C'est ensuite au modèle de les exécuter ; rien n'est fait par cet appel.' This fully discloses that the tool does not execute anything, which is beyond what annotations alone convey. No contradiction.

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 well-structured with clear sections (Quand, Plutôt que, N'appelle aucune API, Returns) and every sentence adds value. It front-loads the purpose, then gives usage context, then clarifies limitations and return type. There is no filler or repetition. The length is justified by the richness of information needed for a workflow tool.

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 workflow tool with no output schema, the description fully specifies the return format ('un runbook en texte — la liste ordonnée des appels Boond à effectuer, avec les filtres exacts') and clarifies that it does not itself execute the calls. Both parameters are fully documented in the schema. The description also covers when to use and when not to use, making it complete for an agent to decide to call and interpret the result. Nothing critical is missing.

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%: both `mois` and `manager_id` have detailed descriptions covering defaults, accepted formats, and resolution behavior. The description does not add parameter-specific information beyond what the schema already provides, but it does reinforce the scope ('Pour un mois et une équipe') and mentions the alternative to avoid an API call. Since the schema carries the full load, a baseline 3 is appropriate.

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 a precise statement of what the tool does: 'Pour un mois et une équipe : qui n'a pas saisi son CRA, qui l'a saisi sans le soumettre, et quels CRA attendent la validation du manager — avec la liste à relancer et les validations à traiter.' It names the specific resource (CRA) and the exact outputs (list to follow up, validations to process). It also distinguishes itself from the alternative prompt `relance_cra` and from sibling workflow tools by its unique focus on CRA follow-up. No ambiguity.

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 explicitly states when to use it: 'Quand : pour dérouler ce scénario multi-étapes sans avoir à retrouver soi-même le bon enchaînement d'outils et les bons noms de filtres.' It also names the alternative: 'Plutôt que : le prompt MCP `relance_cra` si le client l'expose — contenu identique, sans consommer un appel d'outil.' This tells the agent exactly when to prefer this tool over the prompt, fulfilling the highest bar for usage guidance.

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