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

With no annotations, the description carries the full burden and does disclose meaningful behaviors: telephone numbers are dropped, practitioner files are never ingested, filters combine with AND, and each call costs 1 credit. It also clarifies the data source (nightly ODS extracts). This goes beyond the schema, though it omits response format and pagination behavior.

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 description is a single dense paragraph, but every sentence adds value: data coverage, source, exclusions, filter behavior, and cost. It is not overly long for 18 parameters, though the initial enumeration is heavy. The structure is acceptable, but a bulleted list could improve scannability.

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 tool with 18 parameters, no output schema, and no annotations, the description covers content and some behaviors but leaves gaps: pagination defaults, result ordering, and response shape are absent. The filter rule is helpful, but individual parameter semantics are incomplete. It is adequate for basic use but not fully complete for complex queries.

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 compensate, but it only partially does. It explicitly mentions q and the AND-combination rule, and the enumerated fields (ODS code, name, status, postcode, etc.) map to some parameters. However, many parameters such as page, per_page, health_geography, national_grouping, and the date-range filters are not explained individually, leaving their semantics ambiguous.

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 description clearly identifies the resource (NHS ODS register for England) and enumerates covered organisation types and data fields, making it distinctive among the sibling query_* tools. However, it lacks an explicit action verb like 'query' or 'search', so the operation is implied rather than stated directly. The title and name help, but the description itself is more a contents list than a purpose statement.

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?

The description gives no guidance on when to use this tool versus alternatives such as query_uk_care_locations or query_uk_schools. It mentions filter semantics ('Filters combine with AND; q searches all text fields') and cost, but does not state when this tool is preferred or when not to use it. An agent would have to infer NHS-specific usage from the title alone.

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