MailTester Ninja

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

Adds real context beyond the annotations: sequential pattern attempts, first-match-then-stop behavior, a per-pattern cost/verification accounting model, and a paid-API-key requirement. This is exactly the kind of operational and billing context annotations (readOnly/openWorld/idempotent) cannot convey.

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?

Three tight sentences, front-loaded with purpose, then mechanism, then the cost prerequisite. No filler or repetition.

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 tool with a full output schema, annotations covering safety, and a complete input schema, the description covers mechanism, cost, and auth. The only small gap is not clarifying how the optional middle_name alters the search or what happens when no pattern is accepted.

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 coverage is 100% with per-field descriptions, so the schema already carries parameter meaning. The description only loosely ties inputs to 'name and company domain' and doesn't explain the optional middle_name's effect on candidate patterns, so baseline 3 applies.

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 ('Find the work email address of a person') plus the mechanism (pattern guessing against a mail server). It doesn't explicitly name the sibling verify_email, but the 'returns the first address the mail server accepts' phrasing makes the generate-vs-verify distinction inferable.

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 description implicitly scopes usage to someone who knows a name and domain but not the address, and the 'each pattern counts as one verification' line hints at cost. However, it never states when an agent should prefer this over verify_email, nor any exclusion or prerequisite beyond the paid key.

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

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: it is a real-time live server check, no message is sent, and it returns one of three enumerated outcomes including an uncertain catch-all case.

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?

One tight sentence pair: the primary action and mechanism come first, followed by the return-value legend. No filler, though the return-code enumeration could arguably live in the output schema rather than the description.

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 one-parameter read-only check with annotations and an output schema, the description covers what the tool does, how, and what comes back. Only a pointer to the find_email sibling and any latency/rate context is missing.

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 coverage is 100% and the single parameter is fully described in the schema ('The email address to verify'). The description adds nothing about format, normalization, or edge cases, so the schema is doing all the work; baseline 3 applies.

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 gives a specific verb and resource ('Check...whether an email address exists and can receive mail') plus the mechanism (asking the recipient's mail server). It is clear on its own, though it never mentions the sibling find_email, so the agent gets no direct differentiation from 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?

Usage is implied: use it to validate that an address is real and deliverable. There is no explicit when-not guidance, no mention of the find_email alternative, and no note about cost, rate limits, or when 'mb' uncertainty should be treated as acceptable.

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