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

With readOnlyHint=false and openWorldHint=true, the description supplies the missing context: results are 'checked,' contact details are gated behind an account-owner setting in Puley, and the tool reports that state rather than failing silently. It also explains the non-read-only annotation by noting results are 'Saved in the user's Puley history' — a genuinely useful disclosure that annotations alone would not convey. It stops short of describing how verification is performed or what a partially matched result looks like.

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?

The three sentences each carry information, and the return value is front-loaded. But the opening is a noun phrase rather than a verb, the colon after 'checked' reads awkwardly, and 'otherwise this says so' is vague filler that could have been stated concretely as the returned message.

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?

There is no output schema, so the description correctly spends effort on the return: a person, their work email, a verification claim, and the fallback message when contacts are disabled. For a three-parameter lookup this covers what an agent needs, with only the multi-match case and result shape left unstated.

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 0%, so the description must carry the load, and it largely does: 'company (name or website)' clarifies the accepted format, 'role (head of marketing)' gives a concrete example of the expected phrasing, and 'the person's name' is identified as an alternative targeting path. What it omits is the interaction rule between name and role and what happens when neither is supplied.

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?

The description states a specific resource and outcome: 'The person to contact at a company and their work email, checked,' which tells an agent this returns a named contact plus a verified email, not a company profile or a lead list. It does not explicitly distinguish itself from near-neighbours like find_leads or company_brief, so the boundary with siblings is left implicit.

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?

It gives the input recipe ('give the company ... and the role ... or the person's name'), which implies when the tool applies. However it never states when to prefer find_leads or company_brief instead, nor whether role and name are mutually exclusive or can be combined, leaving real selection ambiguity.

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