BurnerCheck

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

Annotations already cover readOnly, idempotent, non-destructive and closed-world. The description adds genuinely new behavioral context: malformed input containing '@' is refused, and the same engine/keys/limits apply as the REST endpoint. That said, it doesn't elaborate on output or failure modes, and output schema exists anyway.

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-loads verb, resource and scope, then enumerates return signals, then the use condition. Every sentence carries weight, though the parenthetical list of detection types is somewhat dense.

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 an output schema present, return values needn't be explained, and the description covers input constraints, detection scope, and rate-limit parity. An agent has what it needs to call this correctly, with only minor gaps in error/edge-case detail.

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 100% and there is a single required parameter, so the schema already documents format and length. The description reinforces the no-'@' rule but adds no syntax or value details beyond the schema – the baseline 3 for full schema coverage 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 (Check) and resource (domain) and enumerates the four things it returns: disposable, free webmail provider, look-alike, and typo suggestion. It also explicitly scopes to a domain with no local part, which cleanly separates it from the check_email sibling.

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?

Gives a clear use condition: 'Use this when you do not need the part before the @.' This routes the agent away from the email-checking sibling, though it does not name check_email explicitly for a fully explicit either/or. No exclusions beyond the @ restriction.

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 and closed-world, but the description adds material behavior beyond them: the address is POSTed and not stored or logged, the check is purely list-based with no DNS/MX lookup, and it shares keys and limits with the REST endpoint. These are exactly the operational facts an agent needs.

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-loads purpose, then layers caveats and privacy notes; each sentence carries information. The parenthetical enumeration is long but is the substantive content, not padding.

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 explained, and the description still supplies the privacy, offline-accuracy and quota context an agent needs to call and interpret the tool correctly. Nothing material 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?

Only one parameter, and schema coverage is 100% with an example and max length already documented in the schema. The description adds no format or syntax guidance beyond what the schema provides, 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 ('Check one email address') and then enumerates exactly what is tested: disposable list membership, role address, free webmail, look-alike domain, syntax, and typo suggestion. This clearly separates it from the sibling check_domain, which operates on a domain rather than an address.

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?

Gives strong context for interpreting results ('List-based and offline: no MX/DNS lookup, so a valid format does not mean the mailbox exists') and notes the shared engine/keys/limits with POST /v1/check. It never explicitly names check_domain as the alternative for domain-only checks, so routing between siblings is left implicit.

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/closed-world, so the bar is lower; the description still adds two things annotations cannot express — that the call does not count against check usage, and that it mirrors GET /v1/meta. Missing are any notes on caching or how stale the returned 'last refresh time' can be, which matters for a metadata tool whose whole purpose is freshness reporting.

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?

Four short sentences, front-loaded with the returned payload, then the three qualifiers (not a check, read-only, REST equivalent). Efficient overall, though the enumerated content list plus the 'Same data as GET /v1/meta' sentence partially duplicate each other.

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 an output schema present, the return-value enumeration is not strictly required, and the description nonetheless supplies the two facts an agent actually needs for selection: no check cost and REST-endpoint equivalence. Nothing critical is missing for a zero-parameter metadata lookup, though freshness semantics of the reported refresh time go 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?

The tool takes zero parameters, so per the rubric the baseline is 4; there is nothing for the description to disambiguate beyond confirming the call is argument-free.

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 opens with a specific verb+resource ('Return the service version and build...') and then enumerates exactly what data comes back (service version, disposable-list version, counts, last refresh, source/licence, limits). This is clearly distinguishable from siblings check_domain and check_email, which return verdicts about a specific input rather than service metadata.

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?

'Does not count as a check' is an explicit routing signal: it tells the agent this call sits outside the check_* quota/accounting path and is safe to call for diagnostics. It stops short of stating when an agent should prefer this over the check tools (e.g. 'use to verify the list is fresh before interpreting a check result'), so it is clear context without explicit usage scenarios.

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