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 disclose a genuinely non-obvious behavior: a do_not_answer refusal path when content has drifted or is unverified, plus 'never guesses.' It does not explain what the refusal payload looks like or what 'drifted' means operationally, but the key behavioral trait is surfaced.

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 semantics — no filler. The parenthetical 'do_not_answer' is slightly cryptic without context but is efficiently placed.

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 one-parameter read tool with no output schema and no annotations, the description covers the refusal behavior but omits both the source of fact_id and any hint about the successful return shape. It is workable but leaves the agent guessing on discovery and output.

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 required parameter fact_id, so the schema adds nothing. The description never explains the id format or, more importantly, that ids must come from credituk_list_facts, leaving the agent to guess where a valid fact_id originates.

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') and scopes it to a domain ('from the credituk pack'), so an agent can match it against the parallel debtuk/pensionuk/etc. getters. It does not explicitly name credituk_list_facts or credituk_changes as the alternatives, so it stops just short of full 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 is only implied: retrieve a single known fact by id, and the 'refuses when drifted or unverified' clause hints at a when-not-to-trust condition. There is no explicit routing guidance telling the agent to use credituk_list_facts to discover ids or credituk_changes to check for updates.

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