Server Quality Checklist

Tool Scores

• risk_policy_lookupA
  3.9/5.0
  Behavior3/5

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

  There are no annotations, so the description carries the full burden. It surfaces that the tool computes/returns policy-derived values and maps inputs to outputs, which is genuinely informative, but it doesn't say whether the data is static, whether lookups can return empty/no-match results, or whether governance constraints are validated at runtime. 3 is fair.

  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?

  One dense sentence with a heavy enumerative tail, but every phrase contributes. Front-loads the return value ('required controls, risk flags...') before diving into the lookup axes. Slightly long but not bloated; the enumeration is useful.

  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 lookup tool with 5 params, 100% schema coverage, and no output schema, the description covers the key decision context (what it returns and on what basis). It doesn't state the output shape, but with no output schema that gap is mostly acceptable, though adding 'returns a list of policy items' would make it 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 input schema already documents every parameter with 100% coverage, so the baseline is 3 per the rubric. The description clarifies the semantic intent behind the parameters as a group (industry/classification/region/deployment drive policy), but adds no individual parameter details 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?

  States a specific verb ('Return') and a specific resource ('required controls, risk flags, and human-in-the-loop triggers for an architecture') and enumerates the dimensions the lookup is based on, clearly distinguishing it from sibling lookup tools such as brand_context_lookup or arch_pattern_lookup. The scope is explicit enough that an agent can tell when to reach for this tool instead of the others.

  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 clearly implies this tool is for policy/risk-oriented lookups and lists the exact inputs that drive the lookup, which gives strong context on when to use it. The only thing missing is an explicit 'use this instead of X when...' statement, but the sibling names (brand_context_lookup, arch_pattern_lookup) are distinguishable from the plain wording.

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

• arch_pattern_lookupA
  4.1/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden of explaining behavior. It discloses that the result is a curated, confidence-scored pattern rather than an unranked list. It does not detail no-match behaviors or side-effect safety, but the lookup-oriented naming and output-focused description make behavior reasonably transparent.

  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 one information-dense sentence with no filler. It front-loads the core matching behavior, then lists the key outputs. It is compact and scannable, though the full list of outputs makes the sentence slightly long.

  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 lookup-oriented tool with no output schema and no annotations, the description adequately explains what inputs shape the match and what the caller receives. It does not cover edge cases like no matching pattern, confidence representation, or return structure, preventing a 5.

  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?

  All five parameters are already described in the schema with 100% coverage, so a baseline 2 is appropriate. The description only lightly reinforces the input dimensions and does not add material relationships or format details 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 uses a specific verb, 'Match', and a resource, 'reference architecture pattern', and identifies the output categories it returns. This clearly distinguishes it from sibling lookup tools like brand_context_lookup and tool_selection_lookup, which target different lookups.

  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 clearly frames the use case: matching an enterprise ask with industry, data stack, cloud, and constraints to a reference architecture. It does not explicitly exclude or compare against sibling tools, but the intended context is clear enough for an agent to select it appropriately.

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

• tool_selection_lookupA
  4.2/5.0
  Behavior3/5

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

  No annotations exist, so the description carries the burden. It discloses that the tool will return 'cloud fit, reasoning, and alternatives,' which gives some behavioral shape, but it does not clarify whether it performs external calls, returns mock versus curated answers, or has any side effects. It describes inputs/outputs but not deeper behavior.

  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?

  A single, dense sentence lists all inputs and outputs without waste. It front-loads the verb and target, and every phrase earns its place. The semi-colon-separated output list is clear to parse.

  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 is sufficient for an agent to prepare the required fields and know what kind of response to expect (recommendation with cloud fit, reasoning, alternatives). Since there is no output schema, describing the response at this level helps. It could add the expected result shape or a mention of staleness provenance, but this is minor.

  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 100%, so the baseline is 3. The description adds meaning by expanding 'constraints' with examples (HIPAA, PII, data residency, SSO/SAML) and by flagging latency as an additional decision factor. This goes beyond the literal schema descriptions and helps an agent populate parameters accurately.

  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 names a concrete verb, 'Recommend', and a specific resource, 'data platform', and enumerates the decision inputs and outputs (cloud fit, reasoning, alternatives). This clearly differentiates the tool from siblings like arch_pattern_lookup and risk_policy_lookup, which concern different domains.

  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 frames when to use this tool: when the agent needs a data platform recommendation given use case, data stack, and constraints. It doesn't explicitly mention alternative tools or exclusions, but the context is clear enough. Sibling names also make the separation obvious.

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

• brand_context_lookupA
  4.4/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the burden. It adds useful behavioral context: the tool sources from Brandfetch plus logo.dev, and serves cached data when sources are unavailable. It could say more about return behavior or failure handling, but this is solid disclosure for a simple retrieval 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?

  Three short sentences with no wasted words. The main purpose is front-loaded, parameters/sources/usage-prerequisite are each given their own concise sentence.

  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 is sufficient for a simple one-parameter read tool. It names the output fields, the source, the fallback cache behavior, and the required input format. A minor gap is the lack of any statement about what happens when no brand context exists for the domain.

  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%, so baseline is 3. The description adds meaning by emphasizing that the domain must be a resolved company domain rather than a partial name, which goes beyond the schema's simple 'string' definition.

  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 a specific verb ('Retrieve'), a clear resource ('company brand context'), and enumerates the exact fields returned. It also specifies the source and input requirement ('resolved domain'), which clearly separates it from the sibling tools by topic.

  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 gives a clear prerequisite: resolve partial company names to a domain before calling. It does not explicitly name alternatives or state when not to use it, but the domain-required condition provides sufficiently clear usage context.

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