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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive, closed world), so the description's job is to add context. It does add genuinely useful behavior: the tool returns an ordered set of exactly 3 dishes plus a dessert, including links. It does not say what happens when filters match nothing or how the ordering is chosen, which keeps it short of a 5.

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?

A single front-loaded sentence that states the action, the exact composition of the result, the ordering guarantee, and the presence of links. No filler, no restatement of the title.

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?

There is no output schema, so the description must describe the return value — and it does, precisely (3 plats + une douceur, ordre conseillé, liens). All five parameters are optional and fully described in the schema. The only gap is edge-case behavior, e.g. fallback when no recipe matches the combined filters.

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 five optional filters (texte, regime, appareil, sansGluten, tempsMaxMin) are already documented in the schema. The description adds no parameter-level meaning at all — notably it never mentions that a diet, appliance, gluten-free, or time constraint can be applied to the session. Baseline 3 is correct when the schema carries the load.

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 (propose) and a specific artifact (une session de batch cooking), and further pins down the output shape: 3 plats différents plus une douceur, dans l'ordre conseillé, avec leurs liens. That composition-oriented purpose is clearly distinct from the sibling tools (chercher_recettes, lire_recette, recettes_avec), though the description never names those alternatives explicitly.

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?

Usage is implied by the purpose — an agent can infer it should call this when a user wants a multi-recipe cooking plan rather than a single recipe. However, there is no explicit when-to-use statement, no when-not-to-use, and no routing to the sibling tools for single-recipe or ingredient-lookup needs.

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