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

Goes well past the annotations: free and account-free, anonymous/trial callers capped at counts under 100 with breakdown cells rounded to the nearest 5, exact small counts gated behind a paid plan, and a disclosure field indicating which regime applied. It also discloses that no contact details are returned, that MCP cross-tabs truncate at 200 cells with GET /v1/counts/{id} holding the remainder, and the Article 6(1)(f) / PECR corporate-subscriber default. Nothing contradicts readOnly/idempotent/non-destructive.

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?

Front-loads purpose and return values before the caveats, and every clause carries non-obvious information. It is a dense single paragraph, though, mixing pricing, rounding, truncation and legal basis into one block rather than separating operational limits from compliance context.

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 free, read-only counting tool with an output schema available, the description still covers the things an agent cannot infer: cost, plan-dependent precision, truncation behavior and the lawful-basis/email-policy default. An agent can decide to call it, chain it into preview_records/quote_order, and set expectations for the response without consulting anything else.

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?

Adds real meaning beyond the 67%-covered schema: the audience argument can be an inline definition or a saved aud_ id, and breakdown_by is capped at three fields returning top 50 cells plus 'other'. The level parameter is only implicitly covered ('UK contacts and companies ... Contacts and companies come back together'), leaving a small gap.

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 ('Counts UK contacts and companies matching an audience') plus the accepted audience forms (inline definition or saved aud_ id). It also enumerates what comes back (Total, New to you, Emailable, breakdowns, quality, compliance summary, price estimate, count id), which separates it from siblings like get_count or preview_records.

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?

Gives explicit timing guidance ('Use it whenever a filter changes') and names two downstream consumers, preview_records and quote_order, that depend on the returned count id, so sequencing is unambiguous. What it lacks is any when-not guidance, e.g. when to use get_count to re-fetch an existing count instead of recomputing.

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