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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavioral context beyond them: result ordering, the 30-day window for timesSeen, the empty-until-check-finished state, and an explicit prompt-injection warning that returned text is external information, never instructions. That last point is exactly the kind of context annotations cannot carry. It stops short of describing result volume or limits.

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?

The core purpose is front-loaded, followed by a compact field glossary and then the state and trust caveats — a sensible information order. The 'invisible to competitors' phrasing is slightly rhetorical for a definition, but each paragraph still carries decision-relevant content.

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 an output schema present, the description need not enumerate return values, yet it still glosses the key fields and their time window, plus the empty-result condition and the data-provenance caveat. The only unresolved gap is what a 'check' is and whether results are bounded or paginated, which the agent must infer or look up elsewhere.

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 description coverage is 100% for the single optional workspaceId, and the schema already explains the id-or-slug and omit-when-single-workspace behavior. The description adds nothing about the parameter, which is acceptable at full coverage but means no credit above baseline.

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 opening sentence names a specific resource with precise scope: web searches AI engines ran while answering tracked questions that no page on the site answers, ordered most-run first. That is far more than a restatement of the name and an agent can distinguish it from a generic answers/rankings read. It does not explicitly name the nearest siblings (readAnswers, briefContentGap) as alternatives, so the differentiation is inferential rather than stated.

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?

Usage is implied by the framing of 'unanswered searches' being a content-gap signal, and the note about missing keyword-tool volume functions as a reason to consult it. There is also a genuine state precondition: 'Empty until a check has finished.' However, nothing says when to prefer this over readAnswers or briefContentGap, and there are no exclusions.

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