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

Goes well beyond the annotations: it discloses provenance (official GOV.UK publication), refresh cadence (every republication, most working days), AND-combination of filters, q's search scope, and, critically, the cost model (1 credit per call, 5-row preview and 20 calls/day without a key). These are exactly the operational facts an agent needs to plan a call and avoid surprise credit burn.

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?

One front-loaded paragraph that leads with what the dataset is, then provenance, granularity, filter logic, and pricing in declining priority. It is dense but each sentence carries information; the field enumeration is slightly redundant with the filter list but earns its place as the return-shape description.

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 does the work of describing the returned columns and row granularity, and it covers access/pricing constraints. The remaining gap is filter value vocabulary (what a valid rating or route string looks like) for a 9-parameter tool with zero schema descriptions.

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 0%, so the description must carry the load; it partially does by naming the concepts behind six filters (organisation, town, county, sponsor_type, rating, route) and explaining that q searches all text fields and that filters AND together. It gives no value formats, no enum hints for rating or route, and says nothing about page/per_page beyond their obvious names.

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: every organisation on the Home Office register of licensed sponsors, with the exact field list and row granularity (one row per organisation and route). This cleanly distinguishes it from the many query_uk_* siblings, which cover companies, charities, schools, etc., none of which are the sponsor register.

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 dataset description rather than spelled out: there is no explicit 'use this instead of query_uk_companies when...' routing, though the sibling names make the domain boundary fairly obvious. The one real exclusion present is 'Organisation-level data only', which tells the agent it cannot resolve individuals.

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