Server Quality Checklist

Tool Scores

• scan_siteB
  3.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full transparency burden, and it does a solid job: it states it is free, requires no API key, enumerates the return scores, and mentions the breadth of checks. It does not explicitly state whether the scan only reads data, but the 'scan' framing plus no-auth emphasizes a low-impact, non-destructive operation.

  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 dense but stays organized: scope first, then returned scores, then additional elements, then technical breadth and cost/auth. It is slightly redundant in repeating '0-100' and 'AI' multiple times, but no sentence is wasted.

  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 thoroughly covers return values and the free/no-key stance, and an output schema exists, so the return shape is further defined. It is incomplete on the input semantics, especially the pages parameter, and does not explain how this scan compares to audit_site, which limits full autonomous invocation confidence.

  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, so the description must compensate, but it only implies a target site without discussing the URL parameter or the pages parameter at all. An agent gets no added meaning for the 'pages' control, which can change the result scope and cost/time.

  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 identifies a specific action (scan a site) and names the exact outputs returned: AEO Score, GEO Score, Agent Readiness Score, and an AI Identity Card. It is distinguishable from compare_sites and fix_sites by the scan-and-report nature, though it does not explicitly differentiate itself from the sibling audit_site.

  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 phrase 'Quick AI visibility scan' and 'Free — no API key needed' imply a lightweight, low-friction initial use case. However, it does not explicitly state when to choose this over audit_site, compare_sites, or fix_site, so the routing decision is left largely to inference.

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

• audit_siteA
  3.7/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the behavioral disclosure burden. It does well by revealing the API key requirement, the cost per call, the returned AI Intelligence Card, and detected competitors. It does not explicitly say the operation is read-only, but 'audit' strongly implies no destructive 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.

  Conciseness4/5

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

  The description is a compact, information-dense paragraph with no filler. The main purpose is front-loaded, and the category breakdown is structured readably. It is lengthy but each clause adds useful information, though the inline list makes the sentence heavier than necessary.

  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 covers the tool's purpose, authentication, cost, output, and high-level scope. However, it leaves parameter semantics unexplained, particularly pages and categories, which are central to configuring the audit. The existence of an output schema mitigates return-value uncertainty, but the request-level gaps remain.

  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%, and the description does not explain the parameters. The url parameter is obvious, but pages and categories are undocumented beyond names/defaults, leaving an agent uncertain about allowed values and semantics. The category list inside the description gives some context, but not enough to correctly set categories.

  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 specific verb and resource: 'Full AI visibility audit' and explains the scope across 58+ checks in 12 categories. It further enumerates the categories and returns, making the purpose concrete and distinguishing it from scanning, comparing, or fixing.

  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 clearly implies this is the tool for a comprehensive AI visibility audit, but it never explicitly states when to use it instead of the sibling scan_site, compare_sites, or fix_site. There is no exclusions or alternative-routing guidance, so the intended usage is only inferred.

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

• fix_siteA
  3.9/5.0
  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 clearly discloses a required API key, cost per call, that output is generated code for coding agents to apply, not an applied change, and the score/ceiling/reference structure. This is good transparency.

  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?

  Each sentence delivers a distinct piece of information: purpose, return value, score projections, content recommendations, format guidance, cost/key. The description is detailed but not bloated, and important usage constraints are front-loaded.

  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 and the simple interface (3 parameters, 1 required), the description is mostly complete: it clarifies behavior, cost, authentication, and output format. It falls slightly short on documenting the 'pages' parameter and on explicit alternatives coverage.

  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?

  Input schema param descriptions are 0% coverage, so the description must compensate. It only mentions how to use 'format' (set to 'claude_code'), and says nothing about 'url' or 'pages'. The meaning of 'pages' is not clarified anywhere.

  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 opens with a specific verb ('Generate') and a clear resource ('complete fix code for all AI visibility issues across AEO, GEO, and Agent Readiness'). This distinguishes it from sibling tools like scan_site or audit_site, which obviously cover diagnosis rather than fix generation.

  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 implicit usage is to generate code fixes after AI visibility issues have been found, but the description does not explicitly state when to use it versus alternatives like scan_site, audit_site, or compare_sites. No exclusion or condition selection is given.

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

• compare_sitesA
  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 burden of disclosure. It discloses the API key requirement, the per-call cost, concurrent scanning behavior, threshold used for competitive gaps, and output includes generated fix code. It does not explicitly state read-only or lack of side effects, but 'scans' and the analysis nature imply non-destructive behavior.

  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 front-loaded with the core purpose and outputs, followed by a clear usage condition and then practical prerequisites. It is a bit dense, but each sentence contributes information about behavior, usage, or costs.

  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 offers enough for an agent to choose and call the tool: purpose, usage triggers, API key, cost, and output summary. An output schema exists, so the need to document return values is reduced. The main lacking aspect is parameter explanations, but those are already penalized in the parameter semantics dimension.

  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 for all parameters. It indirectly maps url and competitor_url via 'two sites concurrently,' but pages is entirely undocumented in both the schema and description. An agent would not know what 'pages' controls, making this clear gap.

  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: 'Competitive gap analysis — scans two sites concurrently, shows side-by-side scores, category-by-category winners, competitive gaps...' This is a specific verb and resource, and it distinguishes compare_sites from sibling tools like scan_site by focusing on two-site comparison and competitor benchmarking.

  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 says 'Use when the user wants to benchmark against a competitor or when scan_site detects competitors in the AI Identity Card,' giving clear triggers for usage. It does not explicitly state when not to use the tool, but the provided context is sufficient to infer it is for competitor comparison rather than single-site audits.

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