storefront

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. Description adds value by revealing data source (College Scorecard) and that it returns score bands/admission rate evidence when available. No contradictions.

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 well-structured sentences: first sentence states core action, second clarifies scope and return. No wasted words, front-loaded.

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 classification tool with 3 parameters and no output schema, the description explains the output (reach/match/safety bands with possible evidence) and data source. Missing error conditions or edge cases, but adequate overall.

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% with clear descriptions for all 3 parameters. The description summarizes the inputs but does not add detailed syntax or format beyond the schema. Baseline 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?

Description uses specific verb '분류합니다' and resource '입시 적합도', clearly stating it classifies reach/match/safety based on College Scorecard data. Sibling tools (capture_lead, get_booking_options, etc.) are distinct, so no confusion.

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?

Description implies use when test scores and target university list are available, and explicitly clarifies it is not a probability prediction ('합격 확률 예측이 아닌'). No explicit when-not or alternatives, but usage context is clear.

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 indicate mutations (readOnlyHint=false) and idempotency (idempotentHint=true). The description adds behavioral context: saves data only after consent, handles email format errors with re-questioning, and provides an onboarding link after save. 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 a single paragraph with the main action at the start, then includes a structured privacy notice. It is not overly verbose but could be better organized. Every sentence adds value.

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 no output schema, the description covers what happens after save (onboarding link), input validation, privacy requirements, and consent procedure. It is complete for a simple lead capture 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 baseline is 3. The description adds meaning: email requires prior consent, interest is optional up to 500 characters, and email format error triggers re-questioning. This is good but not extraordinary.

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: saving email and optional interest for users who want to continue consultation. It distinguishes from sibling tools like assess_admissions_fit or search_mentors, which serve different functions.

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?

Explicitly instructs to call only when user explicitly wants to be contacted, and provides a detailed privacy notice including consent requirements, data collection purpose, retention period, and deletion rights. This gives clear usage 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, idempotentHint, destructiveHint. Description adds value by explicitly stating the tool only provides the link and does not perform booking or payment, which is important behavioral context beyond 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?

Two sentences, each serving a clear purpose: the first lists return values, the second clarifies scope. No wasteful words; front-loaded with key 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 simplicity (1 parameter, no output schema), the description fully covers what the tool returns and its limitations. It is complete for an agent to understand the tool's role and output.

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% with description for mentor_id. Description adds context that mentor_id comes from search_mentors, which is helpful for correct parameter usage, slightly elevating it above baseline 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?

Clearly states it returns session options with durations (15/30/60 min), price, and booking deep link for a specific mentor. Distinguishes itself by noting it only guides the link, not processing booking, setting it apart from sibling tools like capture_lead or search_mentors.

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?

Provides clear context: use after obtaining mentor_id from search_mentors to get booking options. Mentions booking happens externally on goanywhere.guru. However, it does not explicitly state when not to use or list alternatives.

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 adds context beyond annotations: it mentions pagination, explicit null handling for missing data, and that SAT/ACT bands are only present for verified universities. Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description does not contradict 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: the first states the primary function, the second adds important detail about data completeness. No wasted words; information is efficiently front-loaded.

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 no output schema, the description adequately explains return format (paginated, nullable fields). It could explicitly describe pagination behavior (e.g., offset/limit usage) and potential response structure, but the existing detail is sufficient for tool selection.

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 schema already documents all parameters. The description adds value by linking the 'with_test_bands_only' parameter to the behavior of including only universities with verified bands, but otherwise does not significantly extend parameter 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?

The description clearly states it returns a paginated list of universities that support the fit diagnosis (적합도 진단). It distinguishes itself from sibling tools like assess_admissions_fit and search_mentors by focusing on listing supported institutions.

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 context for retrieving supported universities but does not explicitly state when to use this tool over siblings or provide exclusion criteria. It does clarify that certain data fields may be null if not verified, guiding agent expectations.

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?

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses the important fallback behavior: if no exact matches, it relaxes conditions and returns broadened=true with relaxed fields. It also stresses that only actual registered mentors are returned, a meaningful quality guarantee not covered by 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 and front-loaded: the first sentence states the core function and output, the second describes the relaxation behavior. Every clause adds value with no redundancy.

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 description covers the main return fields and the important broadening behavior, which is essential for an agent to interpret results. With no output schema, this provides sufficient context. However, it doesn't explain how the 'limit' parameter affects results, a minor gap given 6 optional parameters.

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%, with descriptions for 5 of 6 parameters. The tool description adds no extra parameter-level details beyond the schema, but it does imply that conditions map to the query parameters. With high schema coverage, the description's lack of additional parameter semantics is acceptable.

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 identifies the tool as searching for GoAnywhere's approved admitted-student mentors, distinguishing it from sibling tools focused on admissions fit, lead capture, booking, or universities. It specifies the returned data (school, major, admission history, rating, profile link) and the key constraint of returning only real mentors.

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 the tool is appropriate (finding real mentors) but does not explicitly mention alternatives or exclusions. The sibling tools are distinct enough that context alone implies usage, but explicit when-not-to-use guidance is missing.

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