Work out how a company builds its email addresses (first.last@, f.last@ …) and apply it to the staff found on its site. Says plainly whether each address is published, inferred or a guess.
| Name | Required | Description | Default |
|---|---|---|---|
| websites | Yes | Company websites or domains (max 25). | |
| maxPagesPerSite | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations available, the description carries the transparency burden and does deliver a meaningful behavioral guarantee: results are explicitly classified as published, inferred, or a guess, so an agent knows not to treat all addresses as verified. It also implies crawling or site inspection, but it stops short of stating failure modes, rate limits, or side effects, so it is not fully transparent.
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 short sentences front-load the primary action and then the output-labeling behavior. There is no filler, no repetition of schema fields, and the structure is easy for an agent to scan.
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?
The core workflow and the confidence classification are described, but the response shape is not specified and there is no output schema. It also leaves maxPagesPerSite unexplained and does not say what happens when no pattern or staff is found, so the description is adequate but not fully self-sufficient.
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?
The schema documents websites well, including the max-25 limit, and the description adds no parameter-specific detail on top of that. maxPagesPerSite is left with only its name, though the description's phrase 'staff found on its site' weakly hints at page-crawling scope.
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 names a specific, non-trivial operation: infer a company's email-address pattern and apply it to staff found on the company website. It also states the distinguishing output, labeling each address as published, inferred, or a guess, which clearly separates it from generic contact-lookup siblings.
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?
The intended scenario is implied: provide one or more company websites and receive patterned, confidence-labeled staff email addresses. However, it never explicitly says when to prefer this over sibling tools like leads_find_contacts or leads_verify_domains, and it gives no exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.