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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely non-obvious behavior: a $0.10 per-call charge settled in USDC on Base via x402, plus a hard 10-result cap — an agent needs both before calling. It stops short of describing response shape or what happens when no filters are supplied.

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 sentences, with the resource and scope front-loaded and the cost/payment constraint appended as a distinct operational sentence. Every clause carries information; nothing is padding.

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?

Without an output schema, the description carries the return-value burden and partially does so by naming director, website check and email details. However, for a five-parameter tool with zero schema documentation, it leaves defaults, the recency window semantics, and unfiltered behavior unexplained.

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 0%, so all five parameters fall to the description. It maps town/postcode/industry to locality/postcode/industry but says nothing about 'max' (its default or cap semantics beyond 'up to 10') or 'days' (the recency window and its 1–30 range), leaving two parameters with no meaning anywhere.

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 resource and scope: newly registered UK companies from Companies House, capped at 10, filterable by town, postcode or industry. The 'newly registered' framing implicitly separates it from siblings like companies_changes and companies_overdue, but no sibling is named explicitly.

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?

No statement of when to use this versus companies_changes or companies_changes_feed, and no prerequisites. The only contextual guidance is operational (cost and payment rail), which is useful but not usage guidance.

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