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

Beyond the readOnly/idempotent/non-destructive annotations it discloses return shape (Companies House fields, compliance facts, contacts by job level), the signed-out null behavior, the deliberate absence of contact details, and the PECR default that excludes sole traders and ordinary partnerships. These are exactly the non-obvious traits annotations cannot express.

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-loaded with what the tool returns and how it differs from siblings, which is the right priority. The tail is dense regulatory prose (legitimate interests basis, PECR subscriber defaults) that is relevant but packed into two sprawling sentences, costing some scannability.

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?

An output schema exists, so return values need not be enumerated, and the description still covers auth state and the contact-count null. The one meaningful omission for correct invocation is the undocumented 'town' narrowing parameter and what to do when a name lookup returns multiple candidates.

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 50% schema coverage the baseline is 3. The description restates the three lookup keys already enforced by the oneOf but adds nothing about the 'town' parameter, name-matching behavior (fuzzy vs exact), or how ambiguity from a name lookup is handled.

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 ('Looks up one company') plus the three lookup keys (Companies House number, domain, name) and what comes back. It explicitly contrasts itself with enrich_contact and count_audience, so an agent can separate this single-company lookup from person-level enrichment and audience counting without opening a 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?

Names both alternatives and the condition that selects each: enrich_contact for one known person, count_audience for everyone at the company. It also states the access condition (free, no account required; contact counts need a signed-in caller) so the agent knows when the useful output is available.

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