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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value by enumerating the four content blocks the response contains (average, evolution, runoff duels, individual polls), which matters because there is no output schema. It does not mention response size or the default history window, which is the only notable gap.

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 compact sentence that front-loads the scope (« Tout ce que les sondages disent d'un candidat ») and then enumerates the payload. No filler, nothing repeated from the schema.

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 only two fully-documented parameters and no output schema, the description carries the burden of explaining what comes back, and it does so by naming the four result sections. Complete enough to call correctly; only the window default and any volume/limit expectations are absent.

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 `candidate` (name, optional accents) and `window` (3m/6m/1a/tout, default 6m) are fully documented in the schema. The description adds no parameter-level detail, so the baseline of 3 applies.

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 precisely what is returned for a candidate: first-round average, evolution, measured second-round duels, and the individual polls the candidate appears in. That is a clear verbless but specific resource+content statement an agent can act on. It does not, however, differentiate itself from siblings like get_polling_average or get_trend, which cover a subset of the same content.

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 phrase « Tout ce que les sondages disent d'un candidat » implies this is the one-stop aggregate and that the sibling tools are narrower slices, but that routing logic is left to inference. No explicit when-to-use or when-to-prefer-a-sibling statement is given.

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