LookupLab

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

Annotations mark readOnlyHint=false, which could mislead an agent into expecting a write; the description usefully clarifies 'Does not change DNS' and explains the real side effect (1 account credit consumed on a successful check). That cost disclosure is real value beyond the annotations, though it says nothing about rate limits or failure 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?

Three short sentences, zero filler, front-loaded with the action and scope; the caveats (no DNS mutation, selector requirement, credit cost) follow in descending order of importance.

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 still needn't detail return values, and it covers the key call prerequisites plus the non-mutation and cost facts. 'Report issues' is a slightly vague characterization of the result, which is the only real gap for a 3-parameter read-style 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 67%, and the one parameter leaving a real gap, selector, is already documented in the schema itself ('required when check is dkim'). The description's enumeration of record types and the selector rule mostly restates the enum and schema text rather than adding new semantics.

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 ('Inspect') plus the exact resources it operates on (MX, SPF, DMARC, DKIM records) and the outcome ('report issues'). This cleanly separates it from siblings like email_verify, ip_lookup, and phone_lookup, which query different resource classes.

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?

It establishes the DKIM preconditions ('DKIM requires a selector') and implies usage via 'user-provided domain', but never says when to choose this over email_verify or ip_lookup. No explicit when/when-not guidance for the sibling set.

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?

Adds substantive behavior beyond the annotations: it costs 1 account credit per successful check, it does not prove mailbox ownership or guarantee delivery, and it does not send email. The credit-cost disclosure is especially valuable because it explains why readOnlyHint is false, something the annotations alone leave ambiguous.

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, each earning its place: capability, limitations, side effects/cost. The core action is front-loaded and there is no filler or restatement 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 one required parameter, no output schema and openWorldHint=true, the description covers capability, cost, and limitations well enough to call correctly. It stops short of hinting at the result shape (e.g. flags versus a single verdict), which is the only remaining gap given no output schema exists.

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 its own description ('Email address to check'). The description adds meaning about what gets done with the address but no format or constraint detail beyond the schema's maxLength/minLength, so the 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 an email address') and enumerates exactly what is inspected: syntax, MX records, disposable-domain and role-address indicators. A sibling list of dns_check, ip_lookup and phone_lookup makes the resource boundary obvious, so an agent can route without opening the 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?

The phrase 'supplied by the user' implies the usage context (validating a caller-provided address), but there is no explicit when-to-use, when-not, or contrast with dns_check, which could also resolve MX records. Usage is inferable but not spelled out.

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=false, destructive=false, idempotent=false and openWorld=true, so the safety profile is covered. The description adds genuinely new operational context: a cost of '1 existing account credit for a successful check' and accuracy caveats ('not a person's precise location or identity', 'privacy flags may be unavailable'). It stops short of rate limits or failure/auth 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?

Three short sentences, front-loaded with the purpose before the caveats and cost. Nothing is padded, though the caveat sentence is doing double duty and could be marginally tighter.

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 and only structured annotations for safety, the description carries the return-shape burden and does so — location, provider indicators, and possibly-missing privacy flags — plus the credit cost. Enough for an agent to call it correctly, though it omits handling for invalid/non-IP input.

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% ('IPv4 or IPv6 address.'), so the schema already documents the single parameter. The description only echoes that the address is user-supplied and adds no syntax, formatting, or validation detail beyond the schema, which is the baseline-3 case.

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: 'look up approximate IP location and network/provider indicators for an IP address.' That clearly scopes it to IPs, implicitly separating it from email_verify and phone_lookup, but it never explicitly distinguishes itself from dns_check, which also operates on IP/network data.

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?

There is no when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. The clause 'supplied by the user' hints that the input is user-provided rather than derived, but an agent gets no routing rule for choosing this over dns_check.

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 cover the general safety profile (readOnlyHint=false, openWorldHint=true, destructiveHint=false, idempotentHint=false), and the description goes well beyond them: exact credit pricing per line type (1 vs 3, +2 for caller name), the up-to-5-credit pre-execution reservation, and an explicit boundary that it places no calls or sends no messages. That is unusually rich disclosure for a paid external lookup, and it is consistent with the non-read-only annotation since credits are consumed.

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 dense sentences, zero filler, with the function front-loaded and the cost/caveat details placed after. Every sentence carries distinct information (capability, caveat, pricing, boundary).

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 two-parameter paid lookup with no output schema, the description covers capability, return attributes, cost, and behavioral boundaries, so an agent can invoke it correctly. It stops short of describing the response shape (e.g., formatting of carrier/line-type fields) or failure behavior on unparseable numbers, which is a minor gap rather than a blocker.

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, but the description adds meaning the schema cannot: caller_name costs an extra 2 credits and returns carrier-listing data rather than verified identity. That materially changes how an agent should decide to set the flag.

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 a user-provided phone number for carrier and line type' — and names the exact attributes returned. The resource (phone numbers) is distinct from the sibling tools email_verify, ip_lookup, and dns_check, so there is no routing ambiguity.

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 caveat that caller-name data is 'a carrier listing, not identity verification' is genuinely useful constraint-setting, and the cost model implicitly frames when the lookup is worth calling. However, there is no explicit when-to-use guidance and no comparison to the sibling lookup tools, so usage is only implied rather than stated.

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