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

Annotations already declare the safe read-only, idempotent, closed-world profile, so the burden is low. The description goes beyond them by disclosing the deterministic decision rule ('la règle de la page « Quel forfait choisir »') and the tie-breaking default ('dans le doute, le Confort'), which is genuinely useful behavioral context an agent would otherwise have to guess.

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?

Dense but well front-loaded: purpose first, then the rule, then the routing conditions. The parenthetical default and the two sibling comparisons each carry weight, though the sentence is long and could be split for readability.

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?

With a single enum parameter, a 100%-covered schema, and no output schema, the description supplies everything needed: input meaning, the deterministic mapping rule, the fallback, and sibling routing. Only a brief note on what the recommendation returns would make it airtight.

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% and the sole enum parameter is fully documented in the schema, so the baseline would be 3. The description beats the baseline by explaining what the ambiguous enum value 'ne_sait_pas' resolves to in practice (the Confort plan), adding decision semantics 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?

States a specific verb (conseille) and resource (forfait Flytel) and immediately scopes the input to current monthly data usage with the three possible states. It is distinguishable from siblings because it names find_best_plan and flytel_estimer_donnees as the tools for other input shapes.

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 states when to use ('quand la personne ne connaît que sa consommation actuelle') and gives two named alternatives with the condition that selects each (besoins chiffrés → find_best_plan; usages comme visio/vidéo → flytel_estimer_donnees). No inference required.

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