Server Quality Checklist

Tool Scores

• manage_leadA
  3.6/5.0
  Behavior3/5

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

  Annotations already indicate this is a non-destructive write operation (readOnlyHint: false, destructiveHint: false). The description adds domain context ('pipeline') and maps the tool to specific business actions. However, it omits error handling (what happens if name doesn't match?), idempotency, or side effects like notifications triggered.

  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 efficient sentences with zero waste. Front-loaded with the core action ('Update a lead's status'), followed immediately by usage examples. Every word earns its place.

  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?

  Appropriate for a 3-parameter tool with 100% schema coverage and annotations present. The description adequately covers the tool's function without needing to explain return values (no output schema). Could improve by mentioning the partial match behavior on 'name' or workflow integration with find_leads.

  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%, providing the baseline. The description reinforces the semantics by mapping the tool to concrete use cases (marking as contacted, adding notes), which helps the agent understand the business logic behind the 'status' enum and 'notes' field, though it doesn't add syntactic details beyond the schema.

  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?

  Clear specific verb ('Update') and resource ('lead's status in the pipeline'). Lists concrete status examples (contacted, replied, not_interested). Deducted one point because it doesn't explicitly distinguish from siblings like 'qualify_leads' or 'score_lead' which might also modify lead data, though the status focus is distinct.

  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?

  Provides usage examples ('Use this to mark leads as...') implying when to use it, but lacks explicit guidance on prerequisites (e.g., using find_leads first to locate the lead) or when NOT to use it vs. alternatives like 'run_pipeline' (likely for bulk operations) or 'qualify_leads'.

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

• qualify_leadsA
  3.7/5.0
  Behavior3/5

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

  Annotations already establish this as read-only and non-destructive. The description adds valuable behavioral context by specifying the scoring algorithm components (fit/intent/urgency) and scope limitation (only unscored leads). However, it fails to clarify what 'qualify' entails regarding data persistence—whether scores are returned in the response, saved to the leads, or how the results should be interpreted.

  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 consists of two highly efficient sentences with zero waste. The first sentence front-loads the core action and scope (batch processing of unscored leads from latest search), while the second provides specific methodology detail. Every word earns its place.

  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?

  For a single-parameter tool with good schema coverage, the description adequately covers the business logic (scoring methodology) and data scope. However, given the lack of an output schema, the description should specify what the tool returns (e.g., scored lead data, qualification status) or how the results are delivered, which would help the agent understand how to use the output in subsequent steps.

  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?

  With 100% schema description coverage for the 'limit' parameter ('Max leads to score'), the schema adequately documents the single input. The description mentions 'all unscored leads' without acknowledging the limit constraint, creating slight ambiguity about whether the tool truly processes all leads or respects the maximum. Baseline 3 is appropriate given the schema carries the documentation burden.

  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 verbs ('Score and qualify') and clearly identifies the resource ('unscored leads from the latest search'). It effectively distinguishes this tool from the sibling 'score_lead' by emphasizing the batch nature ('all unscored leads') and the specific data source ('latest search'), while also detailing the methodology ('rule-based scoring engine' with 'fit + intent + urgency' components).

  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 a workflow dependency by referencing 'the latest search', hinting that this tool processes results from a prior search operation (likely 'find_leads'). However, it lacks explicit guidance on prerequisites, does not clarify when to use this batch tool versus the single-lead 'score_lead' alternative, and omits '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.

• run_pipelineA
  3.9/5.0
  Behavior4/5

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

  Annotations indicate readOnly=false and destructive=false; the description adds valuable behavioral context beyond these binaries by disclosing the exact sequence of side effects (sending invitations and DMs) and noting the implementation script (daily-orchestrator.js), which helps the agent understand the operational scope.

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

  Conciseness4/5

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

  Three sentences efficiently structured: the first front-loads the purpose with clear flow notation, the second provides implementation context (script name), and the third notes the skip parameter. The script reference could be considered extraneous for an AI agent but does not significantly detract from clarity.

  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 the 100% schema coverage and presence of annotations, the description adequately covers the pipeline's behavioral complexity by detailing the 4-stage process. While it could benefit from mentioning idempotency or error handling behavior for a pipeline tool, it sufficiently covers the core operation without needing to describe return values (no output schema).

  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?

  With 100% schema description coverage, the schema fully documents both parameters (skip_leads and dry_run). The description mentions skip_leads explicitly but adds no semantic information beyond what the schema already provides, meeting the baseline for high-coverage schemas.

  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 the specific verb 'Trigger' with the resource 'full daily prospection pipeline' and distinguishes from siblings by enumerating the complete 4-step workflow (find leads → send invitations → check acceptances → send DMs), clearly positioning it as the orchestration tool versus single-operation siblings like find_leads.

  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 by emphasizing 'full' pipeline and listing the complete sequence, suggesting when to use this versus partial operations. However, it lacks explicit guidance stating when to choose this over individual sibling tools (e.g., 'Use this instead of find_leads when you need the complete workflow').

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

• find_leadsA
  4.2/5.0
  Behavior4/5

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

  Annotations indicate external/open-world operation (openWorldHint: true, readOnlyHint: false). Description adds critical implementation context beyond annotations: specifies Playwright for scraping, confirms external data fetching behavior, and discloses authentication requirements not captured in annotations.

  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 structured efficiently: purpose (sentence 1), mechanism (sentence 2), prerequisites (sentence 3). No redundancy or filler; every clause provides distinct operational 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 single-parameter scraping tool, description adequately covers operational prerequisites (LinkedIn session), implementation method (Playwright), and target data (burnout keywords). Missing output specification, but no output schema exists to require such documentation.

  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?

  With 100% schema description coverage for the single 'dry_run' parameter ('Simulate without actually scraping'), the schema carries the semantic load. Description does not mention the parameter, but baseline 3 is appropriate given complete schema coverage per rubric guidelines.

  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 provides specific verb ('Search'), resource ('LinkedIn posts'), and distinct scope ('burnout, stress, or exhaustion'). Clearly distinguishes from siblings like manage_lead or personalize_message which handle post-discovery actions rather than initial scraping.

  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?

  Provides clear prerequisite context ('Requires an active LinkedIn session') implying when-not-to-use. While it doesn't explicitly name alternatives (e.g., 'use manage_lead for existing leads'), the scraping focus and prerequisite guidance provide sufficient contextual guardrails.

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

• personalize_messageA
  4.2/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true (safe computation). Description adds valuable behavioral context: output is 'ready to copy-paste' (indicating it doesn't auto-send), and specifies character constraints (max 200 for invitations, longer for DMs) that clarify output format expectations.

  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 zero waste. First sentence establishes purpose immediately; second sentence provides critical output constraints (character limits, copy-paste ready). Every word earns its place.

  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, description adequately explains return value (copy-paste ready message) and format constraints. With 5 well-documented parameters and clear annotations, description provides sufficient context for invocation, though could explicitly note it generates text without sending it.

  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 high (80%) with detailed enum descriptions in the schema itself (e.g., 'dm2 (follow-up J+3)'). Description reinforces the message_type constraints but doesn't add semantic meaning beyond what's in the schema. Baseline 3 appropriate for high-coverage schemas.

  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 uses specific verb 'Generate' with clear resource 'LinkedIn invitation note or DM'. Explicitly targets 'specific lead' and distinguishes from sibling tools focused on lead discovery/qualification (find_leads, qualify_leads) rather than content generation.

  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?

  Provides clear context by specifying LinkedIn platform and distinguishing between invitation (connection request) and DM use cases. Lacks explicit 'when not to use' or named alternatives, but the distinct action (generate vs. manage/find) makes usage clear.

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

• score_leadA
  4.2/5.0
  Behavior4/5

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

  Annotations establish readOnlyHint=true (safe operation). Description adds valuable behavioral context beyond annotations: discloses the three-factor scoring algorithm (fit/intent/urgency), specifies return format (P1-P4 priority tiers), and mentions recommended offer generation. 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.

  Conciseness5/5

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

  Two sentences with zero waste. First sentence establishes scoring methodology; second discloses return values. Front-loaded with critical information (P1-P4 priority, specific signals like burnout). No redundant or filler content.

  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?

  Adequately compensates for missing output schema by explicitly stating return values (priority tiers P1-P4 and offer recommendations). Covers the 5 parameters sufficiently given 100% schema coverage. Minor gap: does not mention that only 'name' is required while other fields are optional, though this is discoverable in schema.

  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%, providing complete documentation for all 5 parameters (name, title, company, post_snippet, linkedin_url). Description frames these as 'LinkedIn lead' data but does not add syntax, format constraints, or semantic relationships beyond what the schema already provides. Baseline 3 appropriate given high schema coverage.

  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 provides specific verb (Score) + resource (LinkedIn lead) + distinct methodology (fit/intent/urgency with specific signals like burnout/crisis markers). Clearly distinguishes from sibling 'find_leads' (discovery) and 'manage_lead' (CRUD) by specifying analytical scoring function.

  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?

  Provides clear context for when to use through specific scoring dimensions (ICP match, burnout signals, crisis markers), implying this is for nuanced prioritization scenarios. Lacks explicit 'when-not' or direct comparison to sibling 'qualify_leads', but the three specific criteria provide sufficient contextual differentiation.

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

• get_pipeline_statusA
  4.4/5.0
  Behavior4/5

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

  Annotations already establish read-only safety (readOnlyHint=true). Description adds valuable behavioral context by detailing exactly what data fields are returned (invitations sent, DMs sent, acceptance rates, next actions), helping the agent understand the return structure despite no output schema being present.

  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 efficient colon-delimited structure. Front-loaded with action verb, zero filler words. Every element (pipeline scope, specific metrics) earns its place.

  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 zero-parameter status tool without output schema, the description adequately compensates by listing specific return fields (lead counts, rates, actions). Would be perfect if it indicated whether data is real-time or cached, but sufficient for agent selection.

  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?

  Input schema has zero parameters. Per calibration rules, 0 params warrants baseline score of 4. Description appropriately doesn't attempt to invent parameter semantics where none exist.

  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 uses specific verb 'Get' with clear resource 'LinkedIn prospection pipeline' and distinguishes from action-oriented siblings (run_pipeline, manage_lead) by emphasizing it retrieves 'current state' and metrics rather than performing actions.

  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?

  Provides clear context by specifying it returns metrics (lead counts, acceptance rates, next actions), implicitly positioning it as the monitoring tool to use before/after running pipeline actions, though it doesn't explicitly name alternatives or when-not-to-use conditions.

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