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

Beyond the readOnly/idempotent/openWorld annotations, the description discloses the failure mode (PDF-only filers cause the tool to say so and link the filing), conditional field availability ('where published'), a prior-year comparison column, and a cost of 3 credits. Those are exactly the operational facts annotations cannot express, especially the coverage cliff for large companies.

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?

Three sentences, front-loaded with what is returned, then coverage limits, then use cases and cost. Every clause carries information — the field list, the PDF limitation, the credit cost — with no filler or restatement of the tool name.

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 compensates by listing the returned figures and noting the prior-year comparison, plus the partial-result behavior for PDF filers. For a one-parameter read tool with safety annotations already supplied, nothing material an agent needs in order to call it correctly is missing.

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 100% for the single companyNumber parameter, including an example format, so the schema already carries the parameter burden. The description adds nothing about the identifier (no note on format, no cross-reference to company_search for resolving names to numbers), which is the baseline-3 outcome for a fully documented schema.

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-level action (extract headline figures from the latest filed accounts at Companies House) and enumerates the exact resource fields returned: net assets, cash, debtors, creditors, employees, turnover and profit. That field list is what separates it from sibling tools like company_filings (documents) or company_profile (registry data), so an agent can route without opening the schema.

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 gives a concrete use case with decision questions ('use for supplier and credit checks: is it solvent, how much cash, is it growing') and states an eligibility boundary — most small and medium digital filers work, large companies and groups usually don't. It stops short of naming an explicit alternative tool (e.g. company_insolvency or company_charges) or a when-not-to-use rule, so it is clear context rather than full routing guidance.

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