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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description earns credit by disclosing what actually comes back (per-cycle accuracy, MissedTakes Score, sample size, plus current-cycle calls ordered newest first) and that cycle defaults to the current one — details no annotation provides.

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 content and ending with the two lookup modes. Slightly redundant in restating 'their graded election record' immediately after 'One pundit's election record', but nothing is wasted.

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 usefully enumerates the return payload and its ordering. It omits, however, the key ambiguity for a zero-required-parameter tool: what happens when neither slug nor name is supplied, what happens when both are, and what a partial-name match returning multiple pundits yields.

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 100%, so the schema already documents all three parameters including the current-cycle default. The description adds only the framing that name matching is partial rather than exact, which the schema already hints at — baseline 3 is appropriate.

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 the exact resource (one pundit's graded election record plus their calls in a cycle) and enumerates the returned fields (accuracy, MissedTakes Score, sample size), so an agent knows what it is fetching. It does not, however, distinguish itself from the sibling pundit_record, which the near-identical framing makes a realistic source of misselection.

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?

'Look up by slug, or by part of their name' tells the agent how to call it, not when to prefer it. With a sibling literally named pundit_record and another named outlet_record, the absence of any routing guidance (single-pundit vs. aggregate/outlet views) leaves selection to inference.

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