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

With no annotations supplied, the description carries the full burden, and it does disclose one genuinely useful behaviour: the tool can return a do_not_answer refusal when content is drifted or unverified, and will not fabricate. That is real value beyond the schema. However, "drifted" is undefined, and nothing is said about permissions, latency, or what a successful response contains.

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?

Two short sentences, front-loaded with the action and followed by the failure mode. Every clause carries information; nothing is padding.

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?

There is no output schema and no annotations, so the description must cover the return contract, and it covers only the refusal branch. The success shape (what a "fact" looks like when returned) is left entirely unstated. Given the tool's simplicity the refusal disclosure rescues it to adequate, but not more.

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 description coverage is 0% on the single fact_id parameter, so the description must explain it and does not. There is no indication of expected format, whether ids are opaque, or where the agent should obtain a valid id (presumably nhsuk_list_facts). For a one-parameter tool this is the clearest gap.

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?

"Get one verified fact from the nhsuk pack" names a specific verb and resource and the word "one" signals single-record retrieval versus the sibling nhsuk_list_facts. It stops short of naming any sibling explicitly, so the differentiation is implied by the cardinality rather than stated.

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 conveys that this is the lookup path for a single known fact, and the refusal clause hints at the boundary where it should not be relied on. It never says when to prefer nhsuk_list_facts, nhsuk_changes, or the parallel *uk_get_fact tools, so the agent must infer routing from the name and the word "nhsuk".

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