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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds genuinely useful behavior: findings are graded serious/watch/info, each carries a date, plus a one-line summary. With no output schema, disclosing this return shape is valuable. It does not state whether results are time-bounded or how many signals are returned.

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?

A single, front-loaded sentence pair that names the purpose first and then enumerates the signals. No filler or repetition. The trailing 'Matched by company number only' is terse but earns its place as an input constraint.

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 carries the burden of explaining returns and does so adequately: signal categories, severity grades, dates, and a one-line summary. Combined with annotations covering safety and open-world behavior, an agent has enough to call the tool correctly. Missing detail on the grading rubric and result window keeps it from a 5.

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% for the single `company` parameter, so the schema already documents it (number or name, name resolved). The description's 'Matched by company number only' adds a matching-key nuance, but it sits in mild tension with the schema's allowance of a name input and could confuse an agent about accepted formats. Baseline 3 applies when the schema does the heavy lifting.

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 states a specific verb and resource ('what the register shows about a company's health') and enumerates the exact signals returned: status, strike-off proposals, insolvency cases, overdue filings, charges, directors leaving. An agent immediately understands the scope. It stops short of differentiating itself from overlapping siblings like `charges`, `deadlines`, and `late_payment`, which cover some of the same ground.

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 use case (assessing company health/distress) is clearly implied by the content and the serious/watch/info grading. However there is no explicit when-to-use, no exclusion, and no routing to the siblings that overlap it, notably `charges` and `deadlines` which appear to cover portions of this data individually.

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