Server Quality Checklist

Tool Scores

• get_upgrade_diffC
  2.8/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure, but it only states the basic output and filtering option. It does not mention that the diff may be truncated by the maxChars parameter (default 120000), nor does it describe any side effects, permissions, or output formatting. The word 'full' is present but the schema indicates output size is constrained, which could mislead.

  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 a single sentence of 11 words, making it extremely concise and front-loaded with the primary purpose. It contains no redundant information or fluff, scoring high on efficiency, though at the cost of completeness.

  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?

  Given the tool has 6 parameters, no output schema, and no annotations, the one-sentence description is inadequate for understanding the full scope of the tool. It doesn't clarify what the diff contains, how it relates to the sibling tools, or any constraints like the maxChars limit. This is a significant gap for an agent to correctly invoke the 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 only 17% (only 'from' has a description), so the description must compensate. It explains the 'platform' parameter ('optionally filtered by platform'), but gives no meaning for 'to', 'appName', 'maxChars', or 'packageName'. Agents would have to infer the purpose of these parameters from defaults and types, which is insufficient.

  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 uses the specific verb 'Return' and identifies the resource as the 'full Upgrade Helper diff', clearly indicating the tool's output. It also mentions optional platform filtering, which is a key capability, but does not explicitly distinguish this tool from sibling tools like list_changed_files or summarize_upgrade.

  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 description provides no information about when to use this tool versus alternatives. It doesn't mention any contexts where get_upgrade_diff is preferred over get_file_diff or list_changed_files, nor does it exclude any use cases. This leaves the agent without guidance for tool selection.

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

• get_file_diffB
  3.1/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It merely states the action and does not mention output format, constraints like maxChars, error handling, or read-only nature, leaving significant ambiguity.

  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 a single, front-loaded sentence with no waste. It clearly communicates the core purpose in minimal space.

  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?

  Given the absence of output schema and annotations, this description is too thin to fully support tool invocation. It does not explain what the diff contains, the significance of version parameters, or the maxChars limit, and it does not resolve overlap with sibling tools.

  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 description coverage is only 33%, and the description itself adds no parameter details. The schema documents 'from' and 'filePath' but the description does not explain the roles of 'to', 'appName', 'maxChars', or 'packageName', nor compensate for the low 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 the verb 'Return' and the resource 'Upgrade Helper diff for one changed file', which effectively distinguishes this from sibling tools like get_upgrade_diff that likely handle a broader diff scope.

  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 'for one changed file' implies this is for a specific file diff, but there is no explicit guidance on when to use this tool versus alternatives like get_upgrade_diff or list_changed_files. Context is implied rather than stated.

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

• get_upgrade_helper_urlB
  3.1/5.0
  Behavior2/5

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

  With no annotations, the description carries the full transparency burden. 'Build the URL' implies a pure operation, but it does not disclose whether network calls are made, what the output format is, or how invalid versions are handled. The simplicity does not fully compensate for this missing context.

  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 a single, front-loaded sentence with no filler. It states the core action and resource efficiently, making it easy to parse at a glance.

  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?

  For a tool with no output schema and minimal annotations, the description is too sparse. It does not explain return values, parameter roles, or how this URL relates to the upgrade workflow, leaving significant gaps for the agent.

  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 only 25% and the description adds no parameter-level detail. It only implies that 'from' and 'to' are versions, while 'appName' and 'packageName' remain unexplained in both schema and description.

  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 ('Build') and resource ('React Native Upgrade Helper URL'), clearly distinguishing this from sibling tools that operate on files/diffs. It communicates exact scope: producing a URL for a version upgrade, which is immediately actionable.

  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?

  There is no guidance on when to use this tool versus alternatives like 'get_upgrade_diff' or 'summarize_upgrade'. No context is provided for prerequisites, typical workflows, or cases where this URL might be needed.

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

• list_changed_filesB
  3.2/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden. It implies a read-only operation via 'List', but it omits whether this calls an external service, what prerequisites exist, or what the output format looks like. The description provides minimal behavioral detail beyond the action itself.

  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 a single, focused sentence with no fluff. It front-loads the key action and context, making it easy to scan.

  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?

  With 5 parameters, no output schema, and no annotations, the description is far too sparse. It fails to explain parameter roles, expected return format, or how this tool relates to siblings. This is a completely inadequate description for a tool of this complexity.

  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 only 20%, and the description adds little beyond what the schema already provides. 'For a version upgrade' hints at from/to, but appName, platform, and packageName are unexplained in both the schema and description, leaving the agent without meaningful parameter understanding.

  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 action ('List files changed'), the resource ('React Native Upgrade Helper / rn-diff-purge'), and the context ('for a version upgrade'). It distinguishes itself from sibling tools like get_file_diff and get_upgrade_diff by focusing on listing files rather than fetching diffs or summaries.

  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 'for a version upgrade' gives clear context for when to use this tool. However, it does not explicitly name alternatives or provide exclusion criteria, so it relies on the agent to infer from sibling names when this tool is appropriate.

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

• summarize_upgradeB
  3.3/5.0
  Behavior2/5

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

  There are no annotations, so the description must carry the full burden of behavioral disclosure. It only states 'summarize the changed areas' without explaining what that summary includes, the output format, whether it compares versions from/to, or how the optional parameters like appName and packageName affect behavior. The description is too vague to predict the tool's behavior beyond the basic action.

  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 a single, focused sentence that front-loads the verb and clearly names the resource. There is no fluff or repetition, and every word contributes meaning. It is appropriately sized for the information it conveys, though it could be longer to add depth.

  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?

  Given the lack of annotations, output schema, and minimal parameter descriptions, the one-sentence description is insufficient for a tool with four parameters and two required ones. It doesn't specify what 'changed areas' encompasses, what return format to expect, or how the optional parameters influence the summary. The agent would need additional documentation to invoke the tool with 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 schema description coverage is only 25% (only 'from' has an example), and the description does not add any parameter-level meaning. It doesn't clarify the relationship between 'from' and 'to', nor the purpose of appName and packageName. With four parameters and a low coverage baseline, the description should compensate but fails to do so.

  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 summarizes changed areas for a React Native version upgrade, using a specific verb ('summarize') and identifying a distinct resource ('changed areas'). It distinguishes itself from siblings like list_changed_files and get_file_diff by focusing on a high-level summary rather than raw file lists or diffs.

  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 in the context of a React Native upgrade ('for a React Native version upgrade'), which gives a general when. However, it does not explicitly contrast with alternatives like get_upgrade_diff or list_changed_files, nor does it provide any exclusion criteria. The guidance is minimal and implied, not explicit.

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