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

The annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description still adds real context beyond them: 'sans compte ni clé' tells the agent no authentication is needed, and the enumerated payload lists what each offer record contains in the absence of an output schema.

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?

It is front-loaded with the payload contents first and the routing rules second, and every clause carries information. The field enumeration is long but each item maps to a distinct returned value, so it earns its space; only the phrase 'toutes catégories confondues' slightly duplicates the scope already implied.

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 has no parameters, no output schema and no nesting, so the burden falls on describing what comes back and when to call it — the description does both, including verification and expiry dates that an agent would otherwise have to discover by calling.

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?

With zero parameters the baseline is 4, and the description explicitly confirms 'Aucun paramètre', so the agent won't waste a turn probing for filters. Nothing more can be added for a parameterless tool.

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 names a specific verb and resource ('Renvoie la sélection du mois des meilleures offres de parrainage') plus its editorial provenance ('choisies et classées par la rédaction ... toutes catégories confondues'), which immediately separates it from the category- and brand-scoped siblings.

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?

It states the exact triggering condition ('les meilleurs codes de parrainage du moment sans marque ni secteur') and routes the agent to the right alternative in each excluded case: offres_par_categorie for a sector, detail_offre for a brand.

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