api-schema-drift-detector

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'Analyzes' implies a read-only operation, the description does not explicitly state non-mutating behavior, nor does it disclose any edge cases, error conditions, or output format. The list of detections clarifies scope but adds little about actual tool behavior beyond the core purpose.

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

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

The description is a single sentence with a colon-separated list of detection types. It is front-loaded with the primary purpose and every word contributes to understanding. No redundancy or filler.

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

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

The tool has two parameters and no output schema, and the description lists detection types but does not specify the return format (e.g., a list of breaking changes). It also lacks alternative usage guidance. For a moderately complex analysis tool, the description is adequate but leaves gaps around expected output and edge-case behavior.

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

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

The input schema covers 100% of parameters with descriptions ('New (candidate) schema version' and 'Previous (deployed) schema version'). The tool description's mention of 'between two schema versions' aligns with the schema but does not add additional semantic richness beyond what the parameter descriptions already provide. Baseline 3 is appropriate.

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

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

The description clearly states the tool 'Analyzes breaking changes between two schema versions' and lists specific change types it detects (field removal, type changes, newly required fields, etc.). This is a specific verb+resource combination. However, it does not explicitly distinguish itself from sibling tools like drift-detector or schema-validator, relying on the tool name for differentiation.

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

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

The description implies usage when checking schema compatibility by naming the two inputs 'oldSchema' and 'newSchema'. However, it provides no explicit guidance on when to use this tool versus the sibling tools, nor does it state any exclusions or prerequisites. The context is clear enough to infer basic usage, but it lacks direct comparison to alternatives.

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

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 adds valuable context by specifying the exact output categories and their severity levels (error/warning/info), and it mentions recursion into nested objects. While it doesn't detail the output format or error handling, the core behavior is well covered.

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

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

The description is exactly two sentences. The first sentence states the high-level purpose, and the second condenses the behavioral details into a tight list of report categories plus recursion. There is no redundancy or filler, making it exceptionally concise and well-structured.

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

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

Given the tool has simple parameters and no output schema, the description reasonably covers the essential context: what it does, what it detects, and how deeply it traverses. The only gap is the exact return format, but the enumerated report categories give a strong indication of the output. This is adequate for the tool's complexity.

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

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

The input schema already provides 100% description coverage for both parameters ('Expected JSON schema' and 'Actual API response to check against schema'). The description merely reinforces these concepts without adding new usage details, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool's purpose: 'Detects differences between an actual API response and an expected JSON schema.' It uses a specific verb+resource structure and further distinguishes itself from siblings by enumerating the exact categories of differences reported (missing_required, type_mismatch, etc.), which aligns with the drift-detection focus.

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

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

The description provides clear context for when to use this tool—whenever there is a need to compare an actual API response against an expected schema and detect discrepancies. However, it does not explicitly mention alternatives like schema-validator or breaking-change-analyzer, nor does it state when not to use it. Thus it earns a 4 rather than 5.

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

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 explicitly states the return format ('valid:true/false') and the inclusion of an error message on failure, which gives the agent a clear picture of expected outcomes. However, it does not elaborate on edge cases or side effects, though for a validator these are minimal.

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

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

The description is a single, front-loaded sentence that states the core function and output. It contains no unnecessary words or repetition, earning a perfect score for conciseness and structure.

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

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

For a simple validator with two clearly documented parameters and a described output, the description is nearly complete. It lacks explicit usage scenarios or comparisons to siblings, but these are covered by other dimensions. The absence of an output schema is compensated by the inline mention of the return value, making it sufficiently complete.

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

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

Schema coverage is 100% (both 'data' and 'schema' have descriptions). The description adds no extra meaning beyond what the schema already provides, so the baseline score of 3 is appropriate. It neither enriches nor contradicts the parameter definitions.

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

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

The description clearly states the tool's function with a specific verb ('validates') and resource ('data conforms to a JSON schema'). It distinguishes from sibling tools by focusing on validation rather than analysis or detection, leaving no ambiguity about its purpose.

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

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

No guidance is provided on when to use this tool versus alternatives like breaking-change-analyzer or drift-detector. The description implies usage only through its purpose, but there is no explicit mention of scenarios or exclusions, which is a notable gap.

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