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

Annotations already declare readOnlyHint and openWorldHint, yet the description still adds genuinely useful behavior: a hard cap of 100 rows, daily refresh from Companies House, and a paid model ($0.10 per call in USDC on Base via x402). It omits what happens on payment failure or rate limits, and does not point at the free sample sibling, which would complete the picture.

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 dense sentences with no filler: scope and freshness first, then filter dimensions, then cost and payment rail. Every clause carries operational weight for an agent deciding whether to spend $0.10.

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 feed with five optional parameters and no output schema, the definition covers scope, time window, cap, freshness and pricing. The main gap is return shape: with no output schema, the description could say roughly what a row contains beyond the change type.

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 40%, so the description carries partial burden. It maps filters to plain language ('town, postcode, industry and change type') and the 'Up to 100 rows' phrase hints at the max parameter, but it adds no syntax or format detail beyond what the enum and postcode description already supply, and never clarifies locality-versus-town naming.

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-and-resource pair (new director appointments, resignations, PSC changes), a fixed time window ('last 24 hours'), a geography ('UK', 'across all companies') and the filter dimensions. It does not name or differentiate itself from the close siblings companies_changes or companies_changes_feed_sample, so an agent cannot tell from this text alone which of the three to call.

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?

Usage is implied by the 'last 24 hours' framing and the row cap, which suggest a daily-monitoring use case, but there is no explicit when-to-use, when-not-to-use, or reference to the sibling feed_sample or the broader companies_changes tool. The reader must infer routing from the tool name.

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