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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive). The description goes well beyond them: it explains the match key, that a company number resolves registered and former names, that postcode district is checked against the registered office, what statuses appear, and two important limits ('absence never means unsupervised', 'People never loaded'). That is substantive behavioral context an agent cannot infer from the schema or annotations.

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?

Four dense sentences, front-loaded with the core purpose and no filler. The middle sentences are slightly run-on and stack match logic with return-format details, but every clause carries information the agent needs.

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?

With no output schema, the description does the heavy lifting and covers return content, statuses, match semantics, and key limitations. It stops short of noting result-size behavior or pagination for the 'every change recorded' list, which for a possibly large change history would be worth one more clause.

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 100%, so the baseline is 3, but the description adds real meaning beyond the terse schema text: it clarifies that matching is on the name as the register writes it and that passing a company number pulls in registered and former names. The postcode-district check is also explained. This is beyond the schema, though not exhaustive on fuzzy-match fallback behavior.

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 names a specific verb+resource (checking whether a business is on HMRC's Money Laundering Regulations supervised register), and even states what it returns: sector, status, and since when. An agent can distinguish this from siblings like sra_check, cqc_check, or charity_check because the regulator and register are explicit.

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?

It frames interpretation ('HMRC is one supervisor among several, so absence never means unsupervised') which is genuinely useful for when to trust a negative result, but it never names an alternative sibling or states a selection condition against the other regulator-check tools. Usage is implied rather than guided.

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