Server Quality Checklist

Tool Scores

• carbon_footprint_calculatorA
  3.9/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false. Description adds accuracy (±20%), output details, and persona (Émilie). No contradiction, adds moderate extra context.

  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?

  Description is structured with core function first, usage guidance, inputs, persona. Front-loaded but could be more concise; still efficient.

  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?

  Output schema exists and description lists major outputs. But optional parameters (reductionTargets, focus) are not explained, and input requirements could be clearer for a complex tool.

  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?

  Schema description coverage is 0%. Description only says 'company profile and activity data' without detailing any parameter meanings. With 7 complex parameters (nested), more explanation needed.

  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 'calculate a company's greenhouse-gas footprint under the GHG Protocol' with specific output components (emissions breakdown, reduction levers, SBTi trajectory). Differentiates from unrelated siblings like competitor_intel.

  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?

  Explicitly states when to use: 'CSRD compliance pre-audit, green-finance access, or supplier ESG scorecards.' Does not cover when not to use, but context with siblings makes it clear.

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

• pitch_deck_storylineA
  4.1/5.0
  Behavior4/5

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

  Annotations already declare read-only and idempotent behavior. Description adds context: generates 8-20 slides with speaker notes and Q&A, outputs JSON. No contradictions, and no side effects are omitted.

  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?

  Well-structured: starts with action, then output, usage, inputs, and persona. Every sentence adds value, though the persona line is marginally extraneous. Efficient overall.

  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?

  Covers all essential aspects: purpose, usage, input structure, and output format (slides and Q&A). An output schema exists, so return value details are not needed. 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.

  Parameters3/5

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

  With 75% schema description coverage, the baseline is 3. Description generally mentions inputs but adds no new meaning beyond the schema's own descriptions for audience, slideCount, and keyFacts.

  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 explicitly states 'Build a complete investor pitch-deck storyline for a company' with specific verb and resource. It distinguishes from sibling tools like carbon_footprint_calculator by focusing on fundraising presentations.

  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?

  Includes a dedicated 'When to use this tool' section covering fundraise, board meeting, or investor presentation, providing clear context for invocation. Lacks explicit when-not or alternative tool recommendations, but the given guidance is sufficient.

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

• trend_watcherA
  4.1/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral specifics: returns 5-12 trend cards with momentum score, outlooks, opportunity windows, and recommended actions. 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.

  Conciseness4/5

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

  The description is concise (5 sentences) and front-loaded with purpose. The last sentence about 'Delivered by Manue' is informational but not essential. Overall efficient and structured.

  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 purpose, usage, input requirements, output structure, and high-level behavior. Since an output schema exists, the description does not need to detail return formats. It adequately complements the structured fields.

  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% with detailed param descriptions. The description reiterates the inputs but does not add significant new meaning beyond what the schema provides. Baseline of 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 monitors emerging trends, regulatory shifts, and adoption signals for a market sector, with specific output structure. It distinguishes itself from sibling tools (e.g., competitor_intel, carbon_footprint_calculator) by focusing on market trend monitoring rather than other analytics.

  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 includes a 'When to use this tool' section with concrete scenarios (e.g., user asks what is heating up, timing product roadmap, early read on sector). It does not mention when not to use or name alternatives, but provides clear context for usage.

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

• competitor_intelA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context such as generating a report with specific components (e.g., severity scores, quantified recommendations) and the fact that it is delivered by an AI CMO. However, it does not disclose any potential delays or data freshness concerns.

  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?

  The description is a single paragraph that efficiently conveys the tool's purpose, outputs, usage context, and inputs. It is front-loaded with the core output description. While clear, it could be slightly more structured (e.g., bullet points) for easier scanning, but it is appropriately sized.

  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?

  Given the complexity (nested objects, optional focus, array of competitors) and the presence of an output schema, the description is complete. It covers inputs, specific outputs, use cases, and even the authoring persona (Manue, the AI CMO). No additional information seems necessary for an AI agent to use this tool correctly.

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

  Parameters5/5

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

  Schema description coverage is 100% with clear descriptions for selfCompany, competitors, and focus. The description reinforces these inputs, adding detail such as requiring a one-paragraph pitch and a URL for competitors, and noting that focus is optional. This adds value 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 specifies the tool generates a board-ready competitive intelligence report with specific outputs like recent competitor moves, severity scores, pricing radar, recommendations, and a presenter script. This clearly differentiates it from sibling tools (e.g., carbon_footprint_calculator, trend_watcher).

  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 states when to use the tool: 'when the user wants to analyse, benchmark or track competitors, or needs a competitive briefing before a strategic decision.' It provides clear context but lacks explicit guidance on when not to use it or mention of alternatives.

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

• partnership_synergiesA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true, idempotentHint=true, etc. The description adds valuable behavioral context: the tool returns 5-12 results, scores on multiple dimensions, and includes an outreach playbook. It also mentions being delivered by a specific persona (Antoine, AI CSO). This goes beyond annotations, but the description does not discuss rate limits, auth, or side effects, which is fine given the 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?

  The description is concise, approximately 4 sentences, with the most important information first. Every sentence adds value: purpose, output specifics, usage guidance, input explanation, and context. No redundancy or unnecessary details.

  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?

  Given the complexity (5 parameters, nested objects, and an output schema), the description covers the essential inputs (selfCompany, strategicAxis), mentions the output structure (5-12 scored targets with rationale and playbook), and provides usage context. With an output schema present, the description does not need to detail return values, making it complete for agent invocation.

  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 description coverage is 40%, but the description provides additional meaning for key parameters: it explains selfCompany and strategicAxis as inputs, and describes strategicAxis with an example. However, it does not elaborate on nested fields of selfCompany (e.g., name, url, pitch) or constraints, currentPartnerships, focus. The description partially compensates for the low 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?

  The description clearly states it identifies and ranks strategic partnership opportunities, returning 5-12 targets with scores on revenue lift, time-to-impact, integration complexity, and regulatory risk, plus a rationale and outreach playbook. It is specific about the resource (partnership opportunities) and the verb (identify and rank), and it distinguishes itself from siblings like competitor_intel or trend_watcher.

  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 includes explicit guidance: 'When to use this tool: the user wants business-development or alliance ideas, or M&A target screening before deeper due diligence.' This clearly indicates the context. However, it does not explicitly state when not to use or provide alternatives, so it's not a perfect 5.

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