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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial context beyond them: provenance ('official daily public extract'), a privacy boundary of what is never ingested (address lines, phone, email, trustee names), and the billing/preview behavior (1 credit/call, 5-row preview, 20 calls/day). That is exactly the extra agent-relevant behavior structured fields cannot express.

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 dense block, but it is front-loaded with dataset scope and the field inventory is compressed into a single readable run-on rather than scattered sentences. Given the breadth of the record, the length is largely earned; it could be tightened but wastes little.

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 23-parameter, no-output-schema tool the description does well on data content, provenance and cost, and correctly avoids re-explaining return values. The gap is that an agent still cannot confidently populate most filter parameters, so the definition is usable but not fully complete.

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% across 23 parameters with no enums, so the description carries the full burden — but it mostly describes returned fields, not input semantics. Only 'q' (searches all text fields) and AND-combining are explained; value conventions for is_cio, gift_aid, website_present, insolvent, in_administration, reporting_status and charity_type are left entirely to guesswork, as are the date-range and income-range pairings.

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?

Opens with a specific verb+resource and an unambiguous scope: 'Every registered and removed charity on the Charity Commission register for England and Wales.' The dataset boundary is unmistakable against siblings like query_uk_companies or query_uk_sanctions without needing to read any 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?

Gives clear operational context — 'Filters combine with AND; q searches all text fields' plus the credit cost and the no-key preview cap. It does not explicitly name an alternative tool or a when-not-to-use condition, but the dataset is so distinct from the other query_* siblings that no routing guidance is really needed.

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