AiProfile

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

Annotations only declare readOnlyHint and openWorldHint; the description goes well beyond that by disclosing that answers are limited to 'approved Q&As', returned verbatim with sources and approval status, and that unmatched questions surface an available_questions list. The coverage tri-state semantics tell the agent exactly how to interpret partial matches.

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?

Purpose is front-loaded in the first clause, then return semantics, then the prerequisite, which is the right order. The enumeration of coverage values is dense but each clause carries information an agent needs; the only cost is a long single-sentence chain.

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, and the description fully compensates by describing returned fields and the coverage field's three states including the recovery path via available_questions. With the prerequisite and behavior on no-match covered, an agent has everything needed to call and interpret this correctly.

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 descriptions of business_id, question, and language are already documented, giving a baseline of 3. The description adds real meaning beyond the schema by explaining how the question parameter is interpreted for multi-intent inputs and how that yields 'partial' coverage, which the schema does not convey.

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 ('Ask a free-text question about one business') and immediately describes what comes back (best-matching approved Q&As verbatim with sources and approval status). This is clearly distinct from siblings like search_business and get_profile, which find or return profiles rather than answering questions against one.

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 the key sequencing rule: 'Use the business id from search_business,' which tells the agent how to obtain the required identifier. It does not state when to prefer get_profile over a free-text question, so a full when/when-not comparison is absent.

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=true, so safety and openness need no restatement. The description adds genuine behavioral context beyond that: result ranking (full profiles above placeholders) and id stability across get_profile/ask_business. It still says nothing about return shape, pagination, or count behavior for a browse tool whose results may be truncated by 'limit'.

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 the capability, then the trigger, then the behavioral caveats and limits. Every clause carries information: example inputs, ranking rule, id reuse, and the geo/neighborhood exclusion.

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 6-parameter, no-output-schema discovery tool, the description covers purpose, trigger, ranking, id reuse, and unsupported filters, which is most of what an agent needs. Missing are downstream-usable details such as what a result entry contains and how 'limit' affects ranking/truncation.

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 83%, so the baseline is 3 and the per-parameter descriptions already cover city/country/category formats and the min_quality enum. The description corroborates category semantics with an example and hints that quality affects ranking rather than only filtering, but never touches 'limit' or 'language', so it adds little beyond 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?

States a specific verb and resource ('Browse businesses') plus the scoping axes (CATEGORY and place), and the example ('italian restaurant' + 'amsterdam' + 'netherlands') makes the three-way key concrete. The negation 'does NOT know a specific business name' implicitly separates it from the name-oriented sibling search_business, so an agent can route without opening schemas.

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 an explicit trigger condition ('Use when the caller does NOT know a specific business name') and a worked example, and rules out unsupported narrowing with 'Neighborhood and geo filtering are not supported yet.' It does not name search_business as the alternative for the known-name case, leaving that routing inference rather than stated.

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, so safety is covered. The description adds real context beyond that: the response is the complete set of Q&A (implying no truncation/pagination), each item carries sources, and it decodes the 'owner-approved' status as confirmation by the verified business owner — domain semantics an agent cannot get from the 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?

Two sentences, zero waste, with the core operation front-loaded and the parenthetical definition placed exactly where the ambiguous term appears.

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 only two well-documented params, a read-only annotation set, and no output schema, the description does the needed work by sketching the return shape. Minor gaps remain: behavior on an invalid/unknown business_id and the language fallback are 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?

Schema coverage is 100% and both parameters are already documented there, including that business_id comes from search_business. The description restates that provenance but adds nothing about the language parameter (e.g., default behavior when omitted), 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?

Specific verb+resource: 'Read the full profile of one business', and it goes further to name the payload — every question and answer with sources and approval status. That contrasts clearly with the sibling search_business, which finds businesses rather than returning one business's full profile.

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 the business id from search_business' gives the concrete prerequisite and chains the tool to the correct sibling. There is no explicit when-not guidance (e.g., when to prefer ask_business for a targeted question over pulling the whole profile), so it stops short of 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?

The annotations already declare readOnlyHint and openWorldHint, so the description is not responsible for the full safety profile. It adds useful behavior: matching is name-only, and results include a stable id usable with get_profile and ask_business. It does not describe pagination or result-limit behavior, but the core behavior is clear.

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 compact and front-loaded: the purpose comes first, followed by return-ID guidance, an example, and the key exclusion. Every sentence 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?

There is no output schema, so the description appropriately explains that matching businesses and a stable id are returned. It also explains how to use that id downstream. The main remaining gap is result-limit behavior, which is not described.

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 moderate at 67%. The description reinforces that query is a business name with optional city/country and gives a concrete example, but it does not explain the limit parameter or the language parameter's effect. The schema already describes query and language, so the description adds only marginal parameter value.

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 states a specific verb and resource: find a business by name, optionally with city/country. It distinguishes itself from the category-browsing sibling discover_businesses and mentions that returned IDs work with get_profile and ask_business.

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 gives explicit when-to-use guidance: use this for business-name lookup, including an example query, and explicitly excludes category browsing by directing that case to discover_businesses. This is exactly the routing information an agent needs.

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