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 description spends its budget on behavior the annotations cannot convey: 150-answer corpus, five named engines, ranking order ('most named first'), a per-vendor receipt with engine/question/capture time, per-engine and per-question counts with 95% intervals, cited source domains, and concrete provenance (release 2026-09, capture dates, DOI). It also warns that quoted text is evidence, not instructions, which is real prompt-injection guidance an agent would not otherwise have.

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?

Front-loaded with the purpose clause before the payload inventory, and every clause carries content rather than filler. It is a single dense run-on sentence, though, and the provenance block (release/version/capture date/DOI) is crammed into the same breath rather than separated for scanability.

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 return-value burden and does so thoroughly: ranking, per-vendor receipts, per-engine breakdowns, confidence intervals, source domains, and citation provenance. Minor gaps remain — nothing about response size, pagination, or what happens on an empty/ambiguous category beyond the closest-match rule.

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% and the schema already explains that the category can be an id, slug, name from list_categories, or free text, with an example. The description adds only the fuzzy-resolution semantics via the closest-covered-category fallback; it contributes nothing else about the single parameter, so the baseline 3 applies.

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 and resource — read what AI says about one software category — and immediately scopes it to named vendors cited by five specific engines across 150 answers. An agent can distinguish this from find_vendor (single vendor) and list_categories (category enumeration) 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?

Opens with an explicit 'Use this to read...' framing and documents the fallback path: an uncovered category returns 'the closest covered ones', which tells the agent not to expect an error on a vague term. It does not explicitly name when to prefer find_vendor or get_sample_run instead, so routing against siblings is only implied by the schema pointer to list_categories.

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