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

Goes well beyond the annotations (readOnly/idempotent/non-destructive) by disclosing the 25-provider truncation cap, an async 'pending response requires retrying after the supplied delay' pattern, and the important semantic caveat that provider IDs are registered operators, not ultimate owners. These are exactly the traits an agent cannot get from structured fields.

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 and output inventory, then caveats and defaults. Semicolon-packed run-on sentences are dense but every clause carries distinct information; nothing is filler.

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?

No output schema exists, so the description carries the return-value burden and does so by enumerating the response components and the 25-item cap, plus the pending/retry protocol. Slightly incomplete in that it does not describe what fields a provider summary contains, but the shape is clear enough to call correctly.

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 only 50%, but the description compensates by stating that careHome defaults to true and that the filters object follows the same strict semantics as query_dataset. The remaining detail (filter keys come from get_dataset_schema, case-insensitivity) lives in the schema description rather than the tool description, hence not a 5.

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?

Names a specific verb (return) and resource (CQC care-home territory intelligence) and enumerates exactly what comes back: selection totals, providers, beds, coverage, up to 25 summaries. It implicitly contrasts with query_dataset (aggregates/summaries vs. presumably row-level results) but never states the contrast explicitly, so the agent must infer sibling differentiation.

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 context is implied rather than stated: it says it uses 'the same strict filters as query_dataset' and notes careHome defaults to true, which hints at when it applies. There is no explicit 'use this when you want aggregate counts instead of rows' or 'use query_dataset instead when...' routing guidance, and no prerequisites are named.

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