mason

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. It describes the tool as analyzing 'git history' and returning 'aggregate stats', which implies it's a read-only operation that processes data without modification. However, it lacks details on performance (e.g., time complexity, resource usage), error handling, or prerequisites like git repository availability. The mention of 'expensive to compute manually' hints at computational cost but isn't specific.

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 concise and well-structured in two sentences. The first sentence clearly states the action and outputs, while the second adds context about the analysis being 'aggregate stats' and 'expensive to compute manually'. There's no unnecessary repetition or fluff, making it efficient. However, it could be slightly more front-loaded by integrating the cost hint earlier for better clarity.

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's complexity (analyzing git history with multiple outputs) and lack of annotations and output schema, the description is moderately complete. It specifies the analysis type and outputs but doesn't detail return formats, error cases, or dependencies. For a tool with no output schema, it should ideally describe the structure of returned stats (e.g., JSON format, keys), leaving gaps in contextual understanding.

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 has 100% description coverage, with the single parameter 'dir' documented as 'Absolute path to the project root directory'. The description adds no additional parameter semantics beyond this, as it doesn't elaborate on path requirements, format, or constraints. With high schema coverage, the baseline score is 3, reflecting that the description doesn't compensate but also doesn't detract from the schema's information.

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: 'Run git history analysis on a codebase' specifies the verb and resource. It distinguishes from siblings by mentioning 'aggregate stats across hundreds of commits' and specific outputs like 'commit convention patterns, stale directories, and frequently changed files', which suggests a different focus than tools like 'get_code_samples' or 'save_snapshot'. However, it doesn't explicitly differentiate from 'full_analysis' or 'get_impact', which might have overlapping scopes.

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 no guidance on when to use this tool versus alternatives. It mentions that the analysis is 'expensive to compute manually', implying it's for automated processing, but doesn't specify scenarios where this tool is preferred over siblings like 'full_analysis' or 'get_impact'. There are no explicit when-to-use or when-not-to-use instructions, leaving the agent to infer usage from context alone.

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