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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description does add genuinely non-obvious behavior: the date basis for eligible polls is the fieldwork end date, and include_publication_only pulls in otherwise excluded records plus 2026 publisher channel aliases. It leaves out ordering, how limit interacts across the five data categories, and what a zero limit returns.

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, no filler, and the most surprising facts (date basis, publication-only behavior) are placed after the content list. The opening sentence is a bare noun phrase with no verb, which makes the tool's action slightly harder to parse on first read, but nothing is padded or redundant.

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, the description must carry the shape of the response, and it does partially by naming the five data categories returned. However, for a four-parameter tool with an unusual default election_id of 'latest' and a limit that must somehow apply across multiple result sets, an agent still cannot predict the response structure or pagination behavior.

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 coverage is only 25%, so the description carries real weight here. It explains include_publication_only substantively and clarifies the fieldwork-end date semantics that govern filtering, but it says nothing about include_series (series of what?) or about how limit truncates across the five returned categories, leaving two of four parameters unexplained in both schema and description.

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 enumerates the data categories returned (final-week average, retrospective model, initial exit polls, result, recent individual polls) which tells an agent the resource is election polling data, but it never states a verb or the scope of retrieval (a single election? all elections?). It reads as a content manifest rather than a statement of what the tool does, and it draws no boundary against siblings like get_election, get_analytics, or get_summary.

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?

There is no when-to-use guidance and no mention of alternatives, despite a crowded sibling set containing get_election, get_analytics, get_summary, and get_sources that an agent must choose between. The only actionable steer is the note about include_publication_only, which is a parameter behavior rather than usage guidance.

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