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

Goes well beyond annotations (which only declare read-only/idempotent/local) by naming data provenance (daily GIAS extract, monthly Ofsted MI), the join key, deliberate omissions (head-teacher names and phone numbers dropped, governors extract never ingested), and the credit/preview quota behavior. Missing only notes on result ordering or how pagination beyond per_page behaves.

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 what the data is and which fields are returned, then provenance, exclusions, filter semantics and cost. Dense but each clause carries information; only mild redundancy between the field list and the source sentence.

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?

For a 22-param, no-output-schema list tool, the description covers dataset scope, returned fields, filtering model, cost and data-freshness caveats, which is nearly everything an agent needs. The gap is value vocabularies and per-param meaning for the less obvious filters.

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?

With 0% schema description coverage across 22 parameters, the description does carry weight: it maps most params to record fields (URN, name, type, phase, status, local authority, region, address/postcode, trust, Ofsted rating and inspection date) and explains q and AND semantics. But several params remain unexplained — website_present, outward_code, pupils_min/max, establishment_type vs phase, and the expected value vocabularies for status/phase/ofsted_rating (no enums).

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?

Specific verb and resource: queries the DfE GIAS register joined to Ofsted outcomes, and enumerates the returned attributes (URN, type/phase, status, LA, trust, Ofsted rating). It is clearly distinct from the other query_uk_* siblings, which cover unrelated datasets.

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?

Explains operating context: filters combine with AND, q searches all text fields, and gives cost/preview terms (1 credit per call; 5-row preview, 20 calls/day without a key). It doesn't state when to prefer this over a specific alternative, but no sibling overlaps its dataset, so ambiguity is low.

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