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

With no annotations, the description carries the full behavioral burden. It discloses a meaningful operational trait the schema cannot convey: the legal-blackout unavailability window with exact dates. It does not state auth requirements, update cadence, or whether the underlying data is cached, so it stops short of full disclosure.

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 sentences, front-loaded with the returned payload before the availability caveat. Dense but every clause adds information (contents, band, runoff pairs, events, blackout window) with no filler.

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 no output schema and no annotations, the description must describe the return contents, which it does by listing the five data elements. It omits freshness/update frequency and scope limits (e.g., which candidates or polls are covered), a minor gap for a data-retrieval tool.

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, so there is nothing for the description to disambiguate. Baseline 4 applies; no parameter-level detail is required.

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?

Names a specific verb (get) and resource (French presidential 2027, first round) and enumerates the payload: poll average, 95% band, runoff chance per candidate, likely runoff pairs, campaign events. The explicit 'first round' scoping implicitly separates it from the sibling get_france_runoff_2027, though it never names that sibling.

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?

Provides a concrete when-not constraint (unavailable during the legal blackout, with precise Paris-time dates), which is genuinely useful. However, it offers no positive when-to-use framing and never routes the agent to the obvious alternatives (get_france_runoff_2027, list_france_polls_2027), leaving sibling selection to inference.

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