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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds non-obvious content context: only actually measured duels are returned, with margins and a significant/not-significant gap indicator, and no projections — which shapes how an agent should interpret the results.

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?

Two compact sentences: the first defines the data returned, the second immediately rules out the main misinterpretation. No filler, front-loaded, and every clause carries meaning.

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 parameterless, non-destructive read with no output schema, the description adequately conveys what the data is and what it contains (margins, significance). It omits the scope of coverage — which elections/periods and how many duels are returned — which would help an agent know what to expect.

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?

The tool takes zero parameters and the schema is empty with additionalProperties=false, so there is nothing for the description to explain. Baseline 4 applies; no parameter ambiguity exists.

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 — second-round runoff head-to-head polls actually measured by polling institutes, with margins and significance — which clearly differentiates it from an averaged or trend view. It is clear without naming the sibling tools directly.

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?

"Aucune projection ni report de voix" explicitly excludes projections and vote transfers, so the agent knows to use this only for raw measured duels and to look elsewhere for modeled/second-round projections. It stops short of naming get_polling_average or get_trend as the alternatives, so routing is partially inferred.

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