Server Quality Checklist

Tool Scores

• add_resumeB
  3.2/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of disclosing behavioral traits. It does not mention potential overwrites, required prerequisites (e.g., profile existence), side effects, or error conditions. The description is too sparse to inform safe invocation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences with no redundant information. It front-loads the core action and then adds a brief justification for the role_types parameter. Every word earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the absence of an output schema, the description should clarify what the tool returns (e.g., success status, created variant). It also fails to explain the mutual exclusivity of 'path' and 'text' parameters (though the schema notes it). A creation tool requires richer context.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so baseline is 3. The description adds minimal meaning beyond the schema—it mentions 'each variant targets specific role types,' but the schema already describes role_types. No further parameter context is provided.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'Add a new resume variant to the profile.' It also explains the purpose of variants ('target specific role types for automatic selection during fit analysis'), distinguishing it from other resume-related tools like get_resume (view) and list_resumes (list).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description does not provide guidance on when to use this tool versus alternatives (e.g., updating an existing variant or using list_resumes to view variants). No conditions or exclusions are mentioned, leaving the agent to infer appropriate usage.

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

• get_scouted_jobsB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden. It indicates the tool reads from a JSON file and optionally filters, but does not disclose synchronous behavior, response format, or any side effects. Basic transparency for a read operation, but not comprehensive.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences with no wasted words. The first sentence front-loads the main action, and the second adds the optional filter. Efficient and easy to parse.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given no output schema and no annotations, the description adequately explains input but omits details about response structure or fields. For a simple read tool, it is minimally complete but lacks context about what data is returned.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100% for the single parameter, which already explains the filter. The description's 'Optionally filter to only unranked jobs' adds no new meaning beyond the schema, so baseline 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb 'Return' and resource 'scouted job listings', making the tool's purpose evident. However, it does not explicitly distinguish it from sibling tools like 'save_scouted_job' or 'mark_jobs_ranked', which could cause confusion about when to use this read-only tool.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  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. It lacks any context about prerequisites, appropriate scenarios, or exclusions, leaving the agent to infer usage.

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

• update_applicationB
  3.3/5.0
  Behavior3/5

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

  The description notes that last_activity_date is automatically updated, which is useful behavioral context. However, for a mutation tool with no annotations, it lacks details on return values, idempotency, or error handling.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences that front-load the main purpose and add a behavioral note. No wasted words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the absence of annotations and output schema, the description should cover more context, such as return format, required permissions, or input constraints. The auto-update mention is helpful but insufficient.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The description lists the updatable fields but adds no additional meaning beyond what the schema already provides. With 50% schema coverage, the description should elaborate on parameter usage or constraints.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool updates an existing application by ID, distinguishing it from sibling read tools like get_applications and create tools like log_application.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No guidance on when to use this tool versus alternatives (e.g., when to update vs. create). It simply describes the action without context or exclusions.

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

• get_applicationsB
  3.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It indicates read-only behavior and ordering, but does not disclose authorization needs, rate limits, or behavior when no results exist. This is adequate but minimal.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, front-loaded with the main action and ordering, no wasted words. Highly concise while covering core functionality.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple list tool with one optional parameter and no output schema, the description covers the main purpose and filtering. However, it omits details about the return format (e.g., field set) and pagination, though these are less critical given the tool's simplicity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% and the description adds 'Optionally filter by status', but this does not enhance beyond the schema's parameter description. Thus baseline score of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb 'Return' and the resource 'tracked job applications', with ordering and optional filtering. However, it does not explicitly distinguish from sibling tools like 'get_scouted_jobs' or 'get_follow_ups', which have similar retrieval purposes.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No guidance is provided on when to use this tool versus alternatives, nor are there any conditions or prerequisites mentioned. The description simply states functionality without contextual usage advice.

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

• log_applicationB
  3.4/5.0
  Behavior2/5

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

  No annotations provided, so description carries full burden. Discloses the database creation side effect, but lacks details on permissions, idempotency, duplicate handling, or response behavior. Insufficient for a mutation tool.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, no redundancy, front-loaded with the primary action. Efficient and to the point.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With 6 parameters and no output schema, description is too sparse. Missing return value, error conditions, and success/failure indicators. For a creation tool, more completeness expected.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% so baseline is 3. Description adds no extra meaning beyond schema descriptions. No clarification of parameter dependencies or constraints.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action ('log a job application') and the resource ('tracking database'), with a specific verb. It distinguishes from sibling tools like 'update_application' (update vs create) and 'get_applications' (read vs create).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Implies use for logging new applications, but no explicit when-to-use or when-not-to-use. No alternatives mentioned despite many sibling tools. Side effect of database creation is mentioned but lacks guidance on prerequisites.

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

• setupB
  3.4/5.0
  Behavior2/5

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

  No annotations provided, so description must fully convey behavior. It mentions capturing profile and overwrite guard, but does not disclose side effects (e.g., creation vs. overwrite, reversibility, authentication needs, or rate limits).

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences with front-loaded purpose. No wasted words, efficient communication.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Tool has 18 parameters, nested objects, and no output schema. Description is brief, omitting return values, behavior after setup, and any post-conditions. Incomplete for the complexity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, baseline 3. Description only highlights a subset of parameters and adds context for confirm_overwrite (must be true to overwrite). Does not fully compensate for the high parameter count.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description clearly states it's for onboarding by collecting a job search profile. Lists key fields and overwrite behavior. Distinguishes from sibling tools like get_profile (read-only) and update_profile (modification).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Implies use for initial setup, mentions overwrite condition, but lacks explicit guidance on when to use this vs. alternatives like update_profile for edits. No when-not-to indications.

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

• mark_jobs_rankedA
  3.6/5.0
  Behavior2/5

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

  No annotations provided, so the description carries full burden. It indicates a mutation (marking) and returns count, but lacks details on irreversibility, permissions, effects on already-ranked jobs, or potential side effects.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, no wasted words. The main action and return value are front-loaded. Every sentence adds value.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple tool with no parameters and no output schema, the description is largely complete. It specifies scope (all unranked scouted) and output. Minor gap: no mention of idempotency or side effects, but acceptable for this simplicity.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  No parameters exist, so schema coverage is 100%. The description adds value by stating the return type (count), which is not in any schema. Baseline 4 for 0 parameters is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action (mark as ranked), the resource (all unranked scouted jobs), and the output (count). It distinguishes from sibling tools like save_scouted_job (individual) and get_scouted_jobs (retrieval).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No explicit guidance on when to use this tool versus alternatives. It implies usage after scouting jobs, but does not mention prerequisites, conditions, or other options (e.g., marking individual jobs).

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

• update_profileA
  3.7/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It correctly states the merge semantics, but does not disclose potential side effects, permissions, or return value behavior, which is a gap for a mutation tool.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences, front-loaded with the verb and resource, and each sentence adds value. No unnecessary words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite the complexity of 15 parameters nested objects and no annotations or output schema, the description is minimal. It does not explain return values, error handling, or how the merge interacts with existing data, leaving significant gaps for an AI agent.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  With 0% schema description coverage and 15 parameters including nested objects, the description only mentions two example fields ('unlisted_skills', 'dealbreaker_detail'). It adds the merge behavior but does not explain the meaning or constraints of the many other parameters.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states 'Update the user's profile' with a specific verb and resource, and distinguishes from siblings like 'get_profile' and 'setup' by highlighting the merge behavior without full re-setup.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explains that the tool accepts any subset of fields and merges them, implicitly distinguishing it from read tools and full setups. It provides concrete examples like 'unlisted_skills' and 'dealbreaker_detail', but lacks explicit when-not-to-use guidance.

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

• get_profileA
  3.8/5.0
  Behavior3/5

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

  The description implies a read-only operation, but without annotations it does not elaborate on side effects, permissions, or error behavior. For a simple read, this is minimally adequate.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single, direct sentence with no unnecessary words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given no output schema and no parameters, the description sufficiently explains the tool's purpose, though it could mention the nature of the profile data.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  With no parameters, the schema covers everything. Baseline for 0 params is 4, and the description does not detract.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool reads and returns the user profile from a specific file, distinguishing it from siblings like update_profile or get_portfolio.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  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, nor any context or prerequisites.

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

• parse_jdA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that it uses Claude API internally, but does not mention side effects, authentication needs, or rate limits. The return format (structured JSON) is stated, but behavioral boundaries are not fully covered.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences with no wasted words. The first sentence lists output fields, the second explains internal API and purpose. Front-loaded and efficient.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  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 covers return values by listing structured fields. It mentions internal API usage. It could improve by noting input size limits or error handling, but is largely complete for a parse tool with one parameter.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% with one parameter. The description adds 'the full job description text', but this does not go beyond the schema description. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb 'parse' and the resource 'job description', listing specific structured outputs (hard requirements, nice-to-haves, responsibilities, etc.). This distinguishes it from sibling tools like 'analyze_fit'.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage for extracting structured signals before fit analysis, but lacks explicit when/when-not guidance or alternatives. No mention of when not to use this tool vs. siblings like 'analyze_fit'.

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

• search_jobsA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It discloses that the tool does not perform the search and that it reads user profile data to combine with the query. However, it does not mention any side effects, permissions required, or limits (e.g., rate limits).

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise with four sentences, each earning its place: purpose, input, output, and what it does not do. No wasted words, and the key action is front-loaded.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple tool with one parameter and no output schema, the description fully covers what the tool does, its inputs, output, and limitations. An agent can correctly select and invoke it without additional information.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The single parameter 'query' is fully described in the schema ('Free-text search query or keywords to include'). The description adds context about combining with saved profile, but this does not significantly enhance understanding beyond the schema. Schema coverage is 100%, so baseline 3.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool builds an optimized job search query by combining a free-text query with the user's saved profile. It specifies the verb 'build' and the resource 'job search query'. While it does not explicitly differentiate from siblings, the function is unique as a query builder for web search.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description indicates when to use it (for constructing a search query) and explicitly states what it does not do ('Does NOT perform the search itself'). It provides context for using the output with web search tools. However, it does not discuss alternatives or when not to use it.

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

• analyze_fitA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses the main behavior (fetches portfolio and resume, returns bundle, no analysis) but lacks detail on side effects, auth needs, or latency.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences efficiently convey purpose, input, internal operation, and what the tool does not do. No superfluous information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description adequately covers the tool's functionality for aggregating data. It could specify the return bundle structure more precisely, but given no output schema, it is reasonably complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The single parameter has 100% schema coverage with a clear description. The tool description adds no new semantics beyond restating that it accepts a job description, so baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool gathers user data (portfolio and resume) based on a job description and returns a bundle, explicitly distinguishing from siblings like get_portfolio and get_resume that fetch individually.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies when to use (for job fit analysis) and that it does not perform analysis, but does not explicitly list alternatives or when not to use. The mention of internal fetching suggests it is a convenience aggregator.

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

• list_resumesA
  4/5.0
  Behavior3/5

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

  States the read operation and what is returned (labels, target role types) but lacks details on side effects, permissions, or output structure since no annotations and 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Single sentence with no wasted words, directly conveys the tool's purpose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Sufficient for a zero-parameter list tool, though lacking output schema details; no mention of ordering or filtering, but not required for completeness.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  No parameters, so schema coverage is 100%. The description adds meaning by indicating the returned fields (labels and target role types) beyond the empty schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses specific verb 'Return' and resource 'all stored resume variants', clearly distinguishing from siblings like get_resume (singular) and add_resume (creation).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No explicit when-to-use or alternatives mentioned, but the simplicity and zero parameters make it obvious that it's for listing all resumes.

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

• get_follow_upsA
  4.2/5.0
  Behavior3/5

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

  No annotations provided, so description must carry behavioral disclosure. It correctly defines a read operation without side effects, but does not mention output format, pagination, or absence-of-results behavior. Adequate but minimal.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences with no redundant words. Every part is informative: the action, the conditions, and the purpose ('shows what needs attention').

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple read with no params or output schema, the description covers the purpose and filtering. It lacks mention of return fields, but agents can infer from sibling tools. Minor gap.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  With zero parameters, baseline is 4. The description adds value by explaining the filtering logic (date and status) beyond the empty schema, compensating for the lack of param details.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb 'return', the resource 'applications', and includes specific filtering criteria (follow_up_due_date today or earlier, status applied/screening). It effectively distinguishes itself from sibling tools like 'get_applications' which lack this filter.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies usage for viewing applications needing attention. While it doesn't explicitly state when not to use or offer alternatives, the context of sibling tools makes usage clear. A score of 4 reflects the lack of explicit exclusion guidance.

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

• get_portfolioA
  4.2/5.0
  Behavior3/5

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

  No annotations provided, so description must disclose behavior. It reveals that the operation reads public data, returns specific fields, and deep=true costs API tokens. Missing details on auth requirements, rate limits, or failure scenarios, but acceptable given the tool's simplicity.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise (4 sentences), front-loaded with purpose, and every sentence provides essential information without fluff.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given one non-required parameter, no output schema, and no annotations, the description covers the tool's functionality well—returns, deep mode behavior, cost implications. A minor gap: no mention of pagination or limit on number of repos returned.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% (1 param, described in schema). The description adds value by explaining what deep=true does in detail (extracts stack, complexity, etc.) and when to use it, going beyond the schema's basic description.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb ('Fetch') and resource ('public GitHub repos for the user'), and is distinct from siblings like 'get_profile' (user profile) and 'read_repo' (single repo). It is specific and unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicit guidance on when to use deep=true ('when you explicitly need structured analysis and the user has authorized API spend') and when to omit it ('for the free metadata+README fetch'). However, it does not compare to sibling tools like 'read_repo', which might be more appropriate for a single repo.

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

• get_resumeA
  4.3/5.0
  Behavior4/5

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

  The description discloses the source (resume_path from profile), return type (raw text), and supported formats. With no annotations, this transparency is good, though it omits potential failure modes (e.g., file not found).

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences with no unnecessary words. The key points (read resume, source, return type, formats) are front-loaded. Every sentence adds value.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a parameterless tool with no output schema, the description covers what the tool does, where it gets data, and what it returns. It is fully sufficient for an agent to understand and invoke correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  No parameters exist, so the description naturally adds meaning by explaining the data source (saved profile) and file formats. The baseline is 4 as there are no parameters to describe.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool reads the resume file with a specific verb-resource combination. It distinguishes from siblings like get_profile (profile) and add_resume (adding) by focusing on reading the existing resume.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies the tool should be used to read the resume, but does not explicitly state when to use it versus alternatives (e.g., get_profile for profile info, add_resume for uploading). No when-not-to-use guidance is provided.

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

• read_repoA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description fully discloses behavior: it's a local analysis using AST for Python and regex for JS/TS, makes no API calls, and returns raw JSON. It doesn't mention side effects or restrictions, but the tool is read-only by nature, and the description is honest about its methods.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences, front-loaded with purpose, followed by technical approach, then usage recommendation. Every sentence adds value without redundancy. No wasted words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has a single required parameter and no output schema. The description explains what the tool returns (raw structured JSON) and its limitations (no API calls). It covers all necessary context for an agent to understand when to invoke this tool and what it does.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% with a clear description for path. The tool description reinforces that the path is a local repository root directory but adds no new semantic depth beyond what the schema already provides. Baseline 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the verb 'Analyzes a local code repository' and specifies the resource (local repo) and the scope: structural information, languages, tech stack, entry points, modules. It distinguishes from siblings like get_portfolio by noting it provides 'deeper technical signal' and is 'pure local analysis'.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly tells when to use: 'before analyzing job fit' and to supplement get_portfolio. While it doesn't list when not to use, the provided use cases and sibling tools implicitly guide an agent, and it mentions an alternative (get_portfolio). Exclusions are not explicit but the guidance is clear.

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

• get_application_patternsA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses internal use of Claude API, which implies external calls, costs, and potential rate limits. It also describes what the tool does without hiding side effects. No destructive behavior is indicated.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences, front-loading the critical usage condition ('After 10+ applications'). Every clause adds value: the condition, the analysis scope, and the internal API usage. No unnecessary words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given zero parameters and no output schema, the description provides a comprehensive overview of what the tool does and when to use it. It hints at the output by listing example patterns. However, it could specify the output format or any data structure more explicitly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema has zero parameters, achieving 100% schema description coverage trivially. The description adds no parameter info because none are needed. Baseline 4 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool analyzes full application history to find patterns in responses, skills, red flags, and recommended adjustments. It distinguishes itself from siblings like get_applications (which likely lists applications) and analyze_fit (specific job fit) by focusing on aggregate pattern analysis.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly starts with 'After 10+ applications,' providing a clear precondition for use. It doesn't explicitly state when not to use it or compare to alternatives, but the context signal of sibling tools implies differentiation. The guidance is clear but lacks exclusions.

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

• save_scouted_jobA
  4.4/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses behavior: URL validation, deduplication against scouted jobs and applications, and return format. There is no ambiguity.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise and well-structured. Each sentence adds information: saving, validation, deduplication, and return feedback. No unnecessary words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description covers validation, deduplication, and return values. Without an output schema, it explains the return format. It is nearly complete, though it could mention side effects like overwriting the file.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% with parameter descriptions. The tool description adds significant value by specifying acceptable URL patterns and validation logic beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool saves a scouted job listing and validates the URL. It distinguishes from siblings like log_application or get_scouted_jobs by specifying the action of saving with validation and deduplication.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explains what the tool does but does not explicitly state when to use it versus alternatives like log_application. It implies use for tracking job listings but lacks comparative guidance.

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

• purge_dead_listingsA
  4.5/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. It clearly states the tool modifies scouted_jobs.json (destructive), explains detection logic, and notes that connection errors/5xx are kept. It also describes the dry_run safety mechanism. 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences efficiently cover purpose, logic, and dry_run. Front-loaded with main action, no fluff. Every sentence adds essential information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  No output schema, but description explains return behavior (modification or dry-run preview). Covers detection logic, error handling, and parameter use. Complete for a cleanup tool with simple I/O.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema already describes dry_run as boolean to check without modifying. Description adds value by explaining what dry_run does: preview removals without deletion. With 100% schema coverage, baseline is 3, but the additional clarity raises it to 4.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description clearly states the tool checks job URLs for liveness and removes expired/unavailable postings from scouted_jobs.json. It specifies the action (purge), resource (dead listings), and format (scouted_jobs.json). It distinguishes itself from siblings like get_scouted_jobs (read-only) and save_scouted_job (add).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Description provides clear context for when to use: to clean up dead listings from scouted jobs. It details detection methods (HTTP status codes, closure phrases) and warns about false positives (keeping on 5xx/errors). It also introduces dry_run for preview. However, it does not explicitly state when not to use or name alternatives, though the context implies it's for maintenance.

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