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

With no annotations, the description carries the full burden, and it does add real behavioral value by disclosing the do_not_answer refusal path for drifted or unverified facts, which an agent could not infer otherwise. It says nothing about the response shape on success, behavior for an unknown fact_id, or what 'drifted' means operationally.

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, both front-loaded with the operative information (what it returns, and the refusal condition). 'Never guesses' partly restates the preceding clause, a minor redundancy, but overall there is very little waste.

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 single-parameter lookup with no annotations and no output schema, the definition covers purpose and the refusal behavior but omits the return format and id provenance. An agent could call it, but might pick a bad fact_id or misread the do_not_answer sentinel as data.

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% for the single fact_id parameter, so the description must compensate and it does not: it never explains the id format, whether ids are opaque slugs, or how to obtain one. Only the general notion of 'a fact' is conveyed.

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 and resource: 'Get one verified fact from the schooluk pack.' The pack qualifier separates it from the many other domain get_fact siblings (nhsuk_get_fact, pensionuk_get_fact, etc.), but it never mentions schooluk_list_facts or schooluk_changes, so the boundary with its closest siblings is left implicit.

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 only implied: fetch a single fact by id, and expect a refusal rather than a guess when the fact is unverified. There is no explicit statement of when to prefer this over schooluk_list_facts or schooluk_changes, and no guidance on where a valid fact_id comes from.

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