GBG Loqate - Reach

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

Annotations already declare readOnlyHint=true, so the read-only nature is established. The description adds context by specifying the policy categories and that thresholds are included, which goes slightly beyond annotations. However, it does not disclose other behavioral traits like return format, ordering, or pagination, so a mid-range score is appropriate.

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 description is a single sentence that is concise, front-loaded with the verb, and contains no superfluous information. Every word contributes meaning, making it highly efficient.

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 no parameters and simple output, the description is complete. It states the tool lists policies and includes their thresholds, which is sufficient given the readOnlyHint annotation. The absence of an output schema is not problematic because the description conveys the essential content of the result.

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 has zero parameters, so schema coverage is trivially 100%. The description does not need to elaborate on parameter semantics; with no parameters, the baseline for this dimension is 4, and the description provides adequate clarity.

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 clearly states the tool lists available decisioning policies and explicitly names the categories (strict, shipping, standard, permissive) and mentions thresholds. It uses a specific verb ('list') and resource ('decisioning policies'), which distinguishes it from siblings like 'show_policy' and the verification 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?

The description provides no guidance on when to use this tool versus alternatives such as 'show_policy'. It does not mention any contextual scenarios or exclusions, leaving the agent to infer the appropriate use case from the tool's name and description.

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 declare readOnlyHint and openWorldHint, but the description adds critical context: the tool consumes a Loqate credit and the result is reference data, not a verification. This goes beyond annotations. However, the consumption of a credit could be seen as a side effect not captured by readOnlyHint, but it does not contradict it.

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 description is a single paragraph that is information-dense. It front-loads the purpose and includes usage guidance, behavioral notes, and parameter context. Some repetition of 'CONSUMES A LOQATE CREDIT' could be trimmed, but overall it's efficient.

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?

The tool has no output schema, so the description should enumerate the returned address components. It mentions components like organisation, sub-building, number, street, city, province, postcode, country, but does not specify the structure or whether all are always present. This leaves some ambiguity for an agent.

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 baseline is 3. The description adds value by explaining that 'key' is optional if server-configured or if Authorization header is present, and that 'suggestion_id' may become stale requiring a new search. These details help the agent handle errors correctly.

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 clearly states the tool resolves a suggestion id into full address components, using specific verb 'resolve' and resource 'address components'. It distinguishes from the sibling 'verify_address' by explaining the decision vs. reference data use case.

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 explicitly states when to use the tool ('when you need the address itself') and when not to ('to verify a chosen suggestion instead, pass suggestion_id to verify_address'). It also notes the cost of a Loqate credit, guiding the agent to use it sparingly.

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=true and openWorldHint=false, covering the safety profile. The description adds no additional behavioral context beyond "full details," which is vague. No contradiction exists.

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 entire description is one concise, front-loaded sentence with no wasted words. It effectively communicates the tool's purpose in minimal space.

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 simple read-only tool with one well-described parameter and annotations, the description is largely sufficient. However, since there is no output schema, the phrase "full details" is somewhat vague about what exactly will be returned, leaving minor room for improvement.

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 input schema has 100% coverage, with the 'name' parameter description listing the possible values ('strict shipping standard or permissive'). The tool description adds no extra parameter semantics beyond what the schema already provides.

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 clearly states the action (show) and resource (specific decisioning policy), making it distinct from sibling tools like list_policies and the verification tools. The phrase "full details" adds specificity about the depth of information returned.

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 when a specific policy name is known, but it does not explicitly mention when to prefer this over list_policies or any exclusions. No alternative tool is referenced.

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 declare readOnlyHint=true and openWorldHint=true, and the description adds meaningful behavior: policy-driven accept/review/reject, the suggestion feature requiring a separately licensed Loqate feature, error reporting in suggestions.error, and the API key requirement. The schema further details credit consumption for suggestion_id, which is additive and does not contradict the readOnly hint. Slight deduction for not explicitly flagging cost side-effects in the main description.

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 description is a single dense paragraph but every sentence carries distinct information: purpose, outputs, suggest workflow, licensing, and key requirements. It is front-loaded with the main purpose and is appropriately sized for a tool of this complexity. A more structured format (bullets) would earn a 5, but it's already quite efficient.

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?

Given the tool has 45 parameters and no output schema, the description covers the core verification flow, the suggestion handling, and a key error case (suggestions.error). It summarizes return values well enough to set expectations. With 100% schema description coverage and annotations, the overall context is sufficient for an agent to select and invoke the tool correctly. No output schema means a bit more explicit return info could have helped, hence 4.

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%, so the baseline is 3. The description reinforces semantics for key parameters ('Set suggest to also get alternative addresses', 'pass it via the key field') but doesn't add substantial meaning beyond the schema's own detailed parameter descriptions. It adds a small amount of contextual value, hence a 3.

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 clearly states the tool's purpose: 'Verify an address against Loqate's global reference data' with a specific verb and resource. It also lists key return values (confidence score, verification status, recommendation), and the name plus sibling context (verify_contact/email/phone) make its focus on addresses unambiguous.

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 provides explicit guidance for the suggest workflow: enable suggest, offer alternatives to the user, and verify the chosen one in a second call. It also explains when suggestions trigger and the licensing caveat. However, it does not explicitly contrast this tool with sibling verification tools (e.g., when to prefer retrieve_address), so it's not a 5.

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 and openWorldHint, and the description reinforces the safe-read nature while adding substantial behavioral detail: Loqate licensing, API key requirements, credit consumption for suggestion_id, stale-id error behavior, and the suggestions.error reporting. No contradiction with annotations.

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 description is dense but not bloated; it front-loads the purpose and packs the rest into a coherent paragraph. Could be improved with bullets, but every sentence carries operational value given the tool's complexity.

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 47 parameters and no output schema, the description covers the key operational concerns: result shape (individual + overall recommendation), suggestion flow, licensing, key handling, and stale-id behavior. It does not enumerate the return fields, but the no-output-schema context lowers the burden, and the coverage is adequate.

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 covers 100% of parameters, so the baseline is 3; the description adds real operational semantics on top—e.g., suggestion_id must be used instead of address, consumes a credit, stale ids return SUGGESTION_NOT_FOUND, and options booleans are typed differently at the root. This meaningfully augments the schema.

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 'Verify address, email, and/or phone together'—a clear verb and resource scope that immediately distinguishes it from the single-channel sibling tools (verify_address, verify_email, verify_phone). It also states the combined result and recommendation behavior.

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 explains when to use the tool: to verify multiple fields together, and it details the suggestion workflow (call, offer, second verification call). It does not explicitly name sibling alternatives or say 'use this instead of verify_address,' but the 'together' framing plus the workflow guidance implies the appropriate context.

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 and openWorldHint, but the description adds valuable context: it returns specific data (confidence, risk, recommendation) and requires a Loqate API key passed via the 'key' field. This goes beyond the structured annotations without contradicting them.

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 description is two sentences, front-loaded with the primary action and return values, and contains no wasted words. Every element earns its place.

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?

The tool has no output schema, but the description clearly lists the return categories (confidence, risk, recommendation). The key requirement and external service are noted. It does not explain the 'policy' parameter but the schema covers it. Overall, it is adequately complete for a simple verification 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 description coverage is 100%, so the schema already documents all three parameters. The description's mention of the 'key' field merely repeats the schema; it adds no additional semantic value beyond what is already provided.

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 uses a specific verb ('Verify') with a clear resource ('email address via Loqate') and explicitly states the output (confidence, risk level, accept/review/reject recommendation). This distinguishes it from sibling verification tools targeting other resource types.

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 for email verification but provides no explicit guidance on when to choose this over sibling tools like verify_contact or verify_phone. It mentions the API key requirement but not exclusions or alternative scenarios.

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?

The description reveals that the tool calls the external Loqate service, requires an API key, and returns specific data fields (confidence, number type, carrier, recommendation). This adds valuable context beyond the readOnlyHint and openWorldHint annotations, covering auth needs and external dependency. No contradictions with annotations.

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 description is two sentences long, with the core purpose and output in the first sentence and the key requirement in the second. It is front-loaded, direct, and contains no superfluous information.

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?

Given the complete parameter schema, present annotations, and absence of an output schema, the description adequately covers the essential context: purpose, return values, and the API key prerequisite. It could be more complete by mentioning potential error cases or policy defaults, but those are already in the schema. Overall, it provides sufficient information for correct invocation.

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%, so each parameter already has a clear description. The tool description only mentions the 'key' field explicitly, which is already documented in the schema. It does not add additional meaning or clarify parameter usage beyond what the schema provides, so a baseline score of 3 is appropriate.

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 clearly states the tool's action and scope: 'Verify a phone number via Loqate.' This distinguishes it from sibling verification tools (verify_address, verify_email, etc.) by specifying the resource type. It also summarizes the key output components, leaving no ambiguity about purpose.

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 provides clear context for when to use the tool: whenever phone number verification is needed. It does not explicitly name alternatives or exclusions, but the resource-specific language ('Verify a phone number') inherently guides selection. The API key requirement is also stated, which is a practical usage prerequisite.

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