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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds genuinely non-derivable behavior: the external data source (Companies House), per-call cost ($0.05), payment rail (USDC on Base) and protocol (x402). It does not say whether results are paginated or capped in total size, but the cost/auth disclosure is meaningful added context beyond the 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?

Two tight sentences with zero filler, the substantive data scope front-loaded and the cost/payment caveat trailing. Nothing is wasted, though the absence of any clause addressing date-parameter choice is a content gap rather than a verbosity issue.

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 read-only, no-output-schema query tool with three parameters, the description covers the domain scope, source and cost, which is the minimum an agent needs. It still leaves open the return shape (grouped per company or flat), pagination, and the days-vs-since semantics, which matter for correct invocation.

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?

At 33% schema coverage the description must carry the load, and it only partly does: 'up to 20 UK companies' and 'since a date' map to numbers and since, but the `days` parameter is undocumented in both schema and description, and the likely overlap/precedence between `days` and `since` is left entirely unexplained. An agent has to guess how to choose between the two date parameters.

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-object set (director appointments, resignations, PSC changes) over a specific resource (UK companies) and names the source (Companies House). It is distinguishable from companies_new / companies_overdue, but the near-identical sibling companies_changes_feed is never mentioned, so the agent cannot tell from the description alone which of the two 'changes' tools applies.

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?

Scope constraints ('up to 20 UK companies', 'since a date') imply when the tool fits, but there is no explicit when-to-use/when-not-to-use guidance and no routing to companies_changes_feed or companies_changes_feed_sample. Usage must be inferred from the data scope rather than stated.

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