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

Annotations already cover readOnly, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real value by explaining that past runs are read-only records, that covered/excluded flags describe the site today rather than at run time, and that the call is free. It does not mention paging behavior when a run has more topics than one page.

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 with zero padding, and the core statement of what is returned is front-loaded ahead of the supporting notes. Every clause carries information.

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 delegates return shape to get_keywords and clarifies snapshot-vs-current semantics of the flags, which an agent would otherwise get wrong. It stops short of explaining how paging interacts with topics versus keywords, the one remaining gap for a 5-parameter 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?

Schema coverage is 100%, so site, runId, limit, offset and keywordLimit are all documented in the schema itself. The description only restates the runId provenance that the schema already carries and says nothing about the paging or per-topic keyword parameters, so baseline 3 is right.

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?

States a specific verb+resource (retrieves the topics and keywords of one past research run) and distinguishes itself from both siblings it touches: list_research_runs as the source of runId and get_keywords as the shape it mirrors. An agent can tell exactly what this returns without opening a schema.

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?

The parenthetical '(from list_research_runs)' establishes the prerequisite flow, and 'in the same shape as get_keywords' routes agents that already understand that tool's output. No explicit when-not or exclusion is given, so it falls short of a 5.

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