SignupBouncer

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

Annotations already cover safety (readOnly, idempotent, non-destructive) and open-world access, so the bar is lower, yet the description adds real value: live mail-server lookups, that every reason is returned including paid-plan-only ones, and that 'nothing sent is stored.' It omits auth requirements and rate limits, which keeps it from a 5.

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 purpose is front-loaded in the first clause and the paragraph is dense with useful detail rather than filler. The phrase 'the way signupbouncer checks a new signup' is mildly redundant, and the run of output details could be tightened, but overall it earns its length.

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 description need not enumerate return fields, yet it helpfully names verdict, score, reasons, normalised inbox, network, and suggestion. Combined with annotations covering safety, an agent has enough to call this correctly; only error/rate-limit behavior is unaddressed.

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% with only two parameters, so the baseline is 3. The description adds a little meaning, noting the IP's network is used and that the email is normalised (Gmail dots and +tags folded), but that detail concerns output rather than adding syntax or constraints for the inputs.

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: 'Checks one email address, and optionally the signup's IP address,' and frames the scope as a signup-time check. It is easy to separate from siblings like lookup_burner_domain or explain_reason, but it never explicitly names or contrasts those alternatives, so it stops short of a 5.

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 by 'the way signupbouncer checks a new signup' and by the optional IP parameter, so an agent can infer this is the signup-gating check. However there is no explicit when-to-use/when-not guidance and no routing to explain_reason or lookup_burner_domain, leaving the agent to infer the boundary.

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 readOnlyHint/idempotentHint/destructiveHint=false, so the safety profile is covered. The description goes further by describing the shape of the explanation returned (meaning, points, blocking, lowest plan), which is valuable given there is no output schema.

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 with no filler, front-loading the core action and then the returned fields, with the no-argument fallback trailing appropriately.

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 single-parameter, read-only explainer with no output schema, the description fully covers what is returned and the optional-code behavior. Nothing an agent needs to call it correctly 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%, so the code parameter is already documented and the omit-to-list-all behavior is in the schema. The description nevertheless adds multiple concrete example codes (burner_mx, repeat_inbox, datacenter_ip) that help the agent recognize valid inputs.

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 ('Explains a signupbouncer reason code') and enumerates exactly what the answer contains: meaning, point weight, blocking behavior, and plan tier. This clearly separates it from siblings like check_email and lookup_burner_domain.

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 implies usage via the optional-code branch ('Without a code, lists every code'), which tells the agent how to invoke it in both modes. However, it never states when to reach for this tool versus lookup_burner_domain or check_email, leaving sibling routing to inference.

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?

Goes well beyond the annotations by disclosing the API-key env var (SIGNUPBOUNCER_API_KEY), a 1.5-second call limit, and the fail-open behavior ('any failure lets the signup through'). These are exactly the operational traits an agent needs and cannot derive from readOnlyHint/idempotentHint.

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 sentences, front-loaded with what it returns before the usage cue and the behavioral caveats. Every clause carries information an agent needs; nothing is redundant.

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 description needn't detail return values, and the annotations already cover the safety profile. Adding the env var, timeout, and fail-open semantics makes it complete for a code-generation tool.

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 enum values are already documented. The description adds meaning beyond the schema by annotating one value semantically ('supabase (a hook, no code)'), which slightly exceeds the baseline 3 for a fully-covered single parameter.

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?

Names a specific verb and resource: 'Returns the steps and the copy-paste code that checks new signups', with an explicit enumeration of supported stacks. This cleanly distinguishes it from siblings like check_email and lookup_burner_domain, which perform lookups rather than produce integration code.

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?

'Use it when the user is building or changing a signup, register or auth flow' gives a clear triggering condition. It lacks an explicit when-not or a named alternative among the siblings, but the condition is concrete enough to route most calls correctly.

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 readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and offline profile is partly covered. The description adds real value beyond them: it discloses that it consults only preloaded lists with no DNS lookup, returns the harvester observation time, and enumerates the classification categories. It stops short of stating rate limits or return structure, so 4 rather than 5.

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 sentences, front-loaded with the classification purpose and then the key limitation, with no filler. It is dense and information-rich rather than padded, though the enumeration of categories makes it slightly long.

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 carries the burden of describing the return: it conveys the classification outcome and the observation timestamp. That covers what an agent needs to interpret results, though it does not describe the exact response shape or what a negative result looks like.

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 documented in the schema, including the maxLength and the domain-or-email duality. The description's 'Accepts a domain or an email address' merely restates what the schema already says, adding no syntax or format detail. Baseline 3 is correct.

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 (says whether / look up) and resource (domain), and enumerates the exact categories it classifies into: disposable burner list, relay service, free subdomain mail service, or real mailbox provider. It explicitly distinguishes itself from check_email, so an agent can route between the two without opening either 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?

Names the alternative (check_email) and the precise condition that selects it: a brand-new burner domain on a burner mail server is caught only by check_email because this tool uses loaded lists with no DNS lookup. That is an explicit when/when-not statement tied to a sibling.

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