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 fully covered by structured data. The description's added value is telling the agent what the payload contains (per-candidate averages plus margin at each data point), which matters since there is no output schema. It says nothing about granularity, sort order, or how sparse the series may be.

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 sentence with no filler, and the core concept (evolution over time) is front-loaded. Every clause adds a distinct fact: dimension (candidate), and per-reading margin.

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 one-parameter read-only tool with complete annotations, the description covers the content but leaves two gaps: it never references the `window` parameter, and 'la marge' is ambiguous (margin of error vs. lead margin) for a tool that returns per-candidate values. Adequate overall but not fully self-sufficient.

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%: the single enum `window` is fully documented with all four values and the 6m default. The description never mentions the time window, so it adds nothing beyond the schema. Baseline 3 applies when the schema carries the parameter semantics.

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 resource and shape: first-round polling averages over time, broken down by candidate, with the margin at each reading. An agent can tell this is a time-series view rather than a single snapshot. It stops short of naming `get_polling_average` as the point-in-time sibling, so sibling differentiation is only implicit.

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?

Use is implied by the word 'évolution ... dans le temps' – the agent can infer this is the trend view versus the snapshot view. However, there is no explicit 'use this when X, use get_polling_average when Y' routing, and no prerequisites or exclusions stated.

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