B2B Email & Domain Scorer

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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description mainly enumerates return content rather than adding behavior beyond that: it says nothing about lookup latency, rate limits, failure modes, or that no domain is mutated/registered (an open-world external query detail the annotations only imply).

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 tight sentences, front-loaded with the action and the concrete signals returned, then the situational use. No filler or repetition of the title.

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?

With no output schema, the description usefully enumerates what comes back (MX, provider, flags, SPF/DMARC), which is the right level of detail for a lookup tool. The only gap is the unresolved overlap with score_email and what happens when the input is an email versus a domain.

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 only 50% and the 'domain' property has no schema description at all. The description compensates by stating that the parameter accepts a URL or email in addition to a bare domain — information the schema's lone 'stripe.com' example does not convey. 'deep' is still only explained by the schema itself.

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?

Clear specific verb ('Check') plus resource ('company domain') and it enumerates what gets inspected: MX records, mail provider, free/disposable flags, SPF/DMARC. It never names or contrasts with the sibling score_email, and the '(or URL / email)' aside muddies the boundary between the two tools.

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?

'Useful before outreach or when qualifying a lead's company' gives a real usage context, but there is no when-not guidance and no mention of when to prefer score_email instead — despite this tool claiming to accept an email address, which directly overlaps with the sibling.

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 cover readOnly/idempotent/non-destructive/openWorld, yet the description still adds real context: the full action and verdict value sets, the 0-100 score, MX/provider lookup, typo correction, the deep=true SPF/DMARC escalation, and the reassuring 'No mail is sent'. It stops short of stating auth needs, rate limits, or latency/caching behavior.

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 the decision outcome, then outputs, then the deep flag and the no-side-effect note. Dense but each clause carries information; the parenthetical typo example earns its place as an illustration.

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?

With no output schema, the description correctly carries the return-value burden and does so thoroughly (action, action_reason, verdict, score, reasons, MX/provider, typo). It is nearly complete, missing only the meaning of the numeric score bands and any mention of the dns parameter's effect.

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%, so the baseline is 3; the schema already documents email, dns, and deep. The description adds the output-side semantics (send_to carries the corrected address) and clarifies deep, but says nothing about the dns flag beyond what the schema states.

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+resource (score/decide on one lead email) and enumerates the concrete decision space (keep/fix/review/drop) plus the returned verdicts. An agent can distinguish this from score_domain purely on the resource (email vs domain) 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?

Usage context is implied by 'one lead email' and the deep/dns flag hints, but there is no explicit when-to-use vs when-not, and the sibling score_domain is never referenced. An agent must infer the routing from the resource name alone.

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