Server Quality Checklist

Tool Scores

• create_campaignD
  1.6/5.0
  Behavior3/5

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

  The description provides extensive behavioral details (no side effects, idempotency, rate limits, error handling, data privacy). However, it claims read-only behavior while the name implies a mutation, so transparency is partially compromised.

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

  Conciseness2/5

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

  The description is overly long (multiple paragraphs) with repetitive sections (Behavior and Behavioral Transparency overlap). The 'Args' section is verbose and unhelpful. It could be condensed to eliminate redundancy and contradiction.

  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?

  While the description covers rate limits, errors, and privacy, the fundamental purpose mismatch leaves the tool contextually incomplete. The output schema is not described, and the contradiction between name and behavior is not resolved.

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

  Parameters1/5

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

  Schema coverage is 0%. The 'Args' list merely repeats parameter names with uninformative phrases like 'to analyze or process'. No constraints, formats, or examples are added, providing no value beyond the schema.

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

  Purpose1/5

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

  The title and opening line say 'create_campaign' and 'Create an ad campaign', but the 'Behavior' section states the tool generates structured output without modifying external systems, implying it is an analysis tool, not a creation tool. This contradiction makes the purpose misleading.

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

  Usage Guidelines1/5

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

  The 'When to use' section suggests using the tool for structured analysis or classification, which conflicts with the creation name. No alternatives among siblings (e.g., add_creative) are mentioned. The guidance is misleading and does not help the agent decide.

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

• add_creativeD
  1.9/5.0
  Behavior3/5

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

  The description includes a detailed 'Behavioral Transparency' section covering side effects, authentication, and rate limits. However, the core claim of being read-only directly contradicts the tool name 'add_creative', which implies mutation. Extensive detail is provided but undermined by this inconsistency.

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

  Conciseness2/5

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

  The description is verbose with repetitive sections (e.g., behavioral details stated twice). It is not front-loaded effectively; key contradictions emerge later. Several sentences could be merged or removed without loss of clarity.

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

  Completeness1/5

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

  Given the tool's complexity (3 parameters, nested objects, output schema) and the contradictions in the description, the agent cannot determine basic usage. The description fails to reconcile the 'add' and 'read-only' behaviors, making it incomplete for reliable invocation.

  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 coverage is 0%, so the description must compensate. The 'Args' section adds vague descriptions like 'The campaign id to analyze or process' that don't clarify parameter roles. No additional meaning beyond the schema is provided, and the descriptions are inconsistent with the tool's purported function.

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

  Purpose1/5

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

  The description starts with 'Add a creative to campaign' but later claims the tool is read-only and generates structured output without modifying external systems. The 'When to use' section suggests analysis/classification, contradicting the tool name. This is misleading and fails to state a clear purpose.

  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 'When to use' and 'When NOT to use' sections are present but contradictory to the tool's apparent function. The guidance for analysis/classification does not align with the 'add creative' naming, providing no actionable context for when to use this tool over siblings like generate_ad_copy or create_campaign.

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

• generate_headlinesC
  2.9/5.0
  Behavior5/5

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

  A detailed 'Behavioral Transparency' section covers side effects, authentication, rate limits, error handling, idempotency, and data privacy. This fully compensates for missing annotations and gives the agent comprehensive understanding of tool behavior. No contradictions with the tool's nature.

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

  Conciseness3/5

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

  The description is well-structured with bold section headers, but it contains redundancy (e.g., 'Behavior' and 'Behavioral Transparency' overlap) and is longer than necessary. The generic 'Args' section adds little value. A more concise, tool-specific version would be better.

  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 an output schema existing, the description fails to link inputs to headline generation, leaving a completeness gap. The extensive behavioral coverage is positive, but the core function and parameter roles are insufficiently specified. An agent would struggle to understand how to use the parameters correctly.

  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, the description must add meaning. The 'Args' section merely repeats parameter names and adds generic phrases like 'The product to analyze or process', which is unhelpful. No context is given for how 'product', 'platform', 'count', or 'api_key' relate to headline generation.

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

  Purpose2/5

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

  The description starts with 'Generate multiple headlines' but then shifts to generic language about 'structured analysis or classification'. This mismatch between the tool name and the description's focus on analysis undermines clarity. The verb and resource are stated only in the first line, and subsequent sections are inconsistent.

  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?

  Explicit 'When to use' and 'When NOT to use' sections are present, providing some guidance on context and caution. However, the guidelines are generic and do not differentiate this tool from siblings like generate_ad_copy or generate_variants. The advice to use for 'structured analysis' does not align well with headline generation.

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

• generate_ad_copyA
  3.5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and excels. It includes a dedicated 'Behavioral Transparency' section detailing side effects (read-only), authentication, rate limits, error handling, idempotency, and data privacy. No contradictions with missing annotations.

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

  Conciseness3/5

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

  The description is well-structured with sections but is somewhat verbose. The 'Behavior' and 'Behavioral Transparency' sections partially overlap, and the 'Args' list could be more concise. It is front-loaded with purpose, but contains redundancy.

  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 6 parameters, 0% schema coverage, and an output schema, the description covers behavioral aspects well but fails to explain the output or tailor the generic 'analysis/classification' framing to ad copy generation. The output schema exists, so return details are not required, but a brief output description would enhance completeness.

  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%, so the description must compensate. However, each parameter description (e.g., 'The product to analyze or process') is generic and adds no meaningful context beyond the parameter name. For a tool generating ad copy, expected values or constraints are not mentioned.

  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 states 'Generate ad copy for a platform' and expands on behavior, but the 'When to use' section generalizes to 'structured analysis or classification', which slightly conflicts with the tool name. It does not distinguish from siblings like generate_headlines or generate_variants.

  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 provides explicit 'When to use' and 'When NOT to use' sections, but does not compare to sibling tools or give specific scenarios for this tool versus alternatives. Guidance is present but generic.

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

• get_best_performingA
  3.5/5.0
  Behavior5/5

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

  Thoroughly details side effects, authentication, rate limits, error handling, idempotency, and data privacy, far exceeding what annotations would provide. No annotations exist, so description fully compensates.

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

  Conciseness3/5

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

  Well-structured with sections, but lengthy and contains redundancy (e.g., Behavior and Behavioral Transparency overlap). Could be more concise.

  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?

  Covers most aspects but lacks specificity on what 'best performing' means (metrics, criteria) and does not use the output schema to offset explanation. Adequate but incomplete for a tool with 3 parameters and rate limits.

  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%, but the description's 'Args' section only repeats parameter names and types with generic phrases like 'The campaign id to analyze or process.' No meaningful semantics added beyond schema defaults.

  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 it retrieves best-performing creatives, but does not explicitly differentiate from sibling tools like 'get_performance' or 'get_campaign'.

  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 general when/why to use and not use, but lacks direct comparison to alternative tools. It gives context but not specific tool selection guidance.

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

• optimize_copyA
  3.7/5.0
  Behavior5/5

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

  With no annotations provided, the description takes full responsibility for behavioral disclosure. It thoroughly covers side effects (read-only, stateless), authentication (none for basic, pro/enterprise requires API key), rate limits (10/day free, unlimited pro), error handling (structured errors), idempotency, and data privacy. This is exceptional transparency.

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

  Conciseness3/5

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

  The description is well-structured with clear sections, and the first sentence is front-loaded with the purpose. However, there is redundancy between the 'Behavior' section and the 'Behavioral Transparency' section, repeating read-only and idempotency details. It could be trimmed by about one-third without losing meaning.

  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?

  The description adequately covers usage and behavior for a tool with an output schema (so return values are handled externally). However, the parameter descriptions are weak, leaving the agent without enough context to correctly set 'target_metric' or understand the role of 'api_key'. This gap reduces completeness.

  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%, so the description must clarify parameter meanings. However, the 'Args' section only repeats parameter names and adds generic phrases like 'to analyze or process' for all three parameters. No examples, valid values, or context are given for 'creative_id' or 'target_metric'. The default for 'target_metric' ('ctr') is not explained.

  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 optimizes existing copy based on performance, and further clarifies it performs structured analysis or classification. The name 'optimize_copy' combined with the first sentence provides a clear verb+resource. However, the phrase 'against established frameworks or standards' is somewhat generic and could be more specific to copy optimization.

  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 'When to use' and 'When NOT to use' sections, providing clear guidance. It warns against real-time production decision-making without human review. However, it does not directly compare to sibling tools like 'generate_ad_copy' or 'get_best_performing', so the agent would need to infer differentiation.

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

• get_campaignA
  3.8/5.0
  Behavior5/5

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

  With no annotations provided, the description fully covers read-only, idempotent, stateless behavior, authentication, rate limits, error handling, and data privacy. Excellent detail.

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

  Conciseness3/5

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

  Well-structured with clear sections, but contains redundancy (e.g., 'Behavior' and 'Behavioral Transparency' overlap). Could be more concise without sacrificing important details.

  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 presence of an output schema, the description adequately covers behavior, auth, rate limits, and error handling. It could briefly mention what kind of details are returned (e.g., campaign settings, metrics), but overall complete.

  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 coverage is 0%, so description must compensate. The 'Args' section provides only generic descriptions ('The campaign id to analyze or process.') that add minimal meaning beyond the parameter names.

  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?

  Clearly states it gets campaign details and is read-only. However, it does not differentiate from sibling tools like get_performance or get_best_performing, relying on a generic 'structured analysis' purpose.

  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 explicit 'When to use' and 'When NOT to use' sections, giving clear context for appropriate invocation. However, it lacks references to alternative sibling tools, which would improve guidance.

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

• generate_variantsA
  4/5.0
  Behavior5/5

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

  With no annotations provided, the description fully compensates by detailing side effects (read-only, no side effects), authentication, rate limits, error handling, idempotency, and data privacy in a dedicated 'Behavioral Transparency' section. This is comprehensive and exceeds typical expectations.

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

  Conciseness3/5

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

  The description is well-structured with clear sections but contains redundancy (e.g., 'Behavior' and 'Behavioral Transparency' overlap). The 'Args' list adds no value beyond the schema, making it less concise than it could be.

  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?

  While the description covers usage, behavior, and limitations adequately, the parameter descriptions are vague, and the output format is not explained despite having an output schema. This leaves gaps for a tool generating ad variants, especially relative to sibling tools.

  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 input schema has 0% description coverage, and the 'Args' section merely repeats parameter names with generic phrases like 'to analyze or process', adding no meaningful context. The description fails to explain what each parameter actually represents or how to use it effectively.

  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 'Generate multiple ad variants for A/B testing', which clearly specifies the verb (generate), resource (ad variants), and purpose (A/B testing). This distinguishes it from sibling tools like 'add_creative' or 'generate_ad_copy'.

  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 dedicated 'When to use' and 'When NOT to use' sections, providing clear context for appropriate usage. However, it does not explicitly discuss alternatives among sibling tools, which would improve differentiation.

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

• get_performanceA
  4.1/5.0
  Behavior5/5

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

  With no annotations, the description fully covers behavioral aspects: side effects (read-only), authentication, rate limits, error handling, idempotency, and data privacy. This is comprehensive and leaves 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.

  Conciseness4/5

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

  The description is well-structured with clear sections but is somewhat verbose. The 'Behavior' and 'Behavioral Transparency' sections overlap, causing repetition. A more streamlined version would be equally informative.

  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 presence of an output schema, the description adequately covers behavioral context and usage. However, it lacks specifics about the metrics returned (e.g., dimensions like clicks, impressions) and the 'When to use' guidance is generic. Slightly incomplete for full agent comprehension.

  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 input schema lacks descriptions (0% coverage), and the description's 'Args' section only repeats parameter names with generic phrases like 'The campaign id to analyze or process.' It fails to explain the purpose or expected format of each parameter, especially 'api_key' which is described as something to 'analyze' rather than authenticate.

  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 'Get creative performance metrics' with a specific verb and resource. It distinguishes from siblings like 'get_best_performing' by focusing on general performance data.

  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 when-to-use and when-not-to-use sections, providing context for appropriate usage. However, it does not compare directly to sibling tools like 'get_best_performing' or 'get_campaign', which would further clarify when to choose this tool.

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