corpus_stats

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 reveals the output nature (counts by pack/kind, disk size) but doesn't disclose whether this is read-only, how it handles an empty corpus, execution cost, or what 'pack' and 'kind' refer to. For an analytical tool this is thin coverage.

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 short sentence that efficiently conveys the tool's informational scope. No wasted words, though it could be slightly more explicit about the verb (report, summarize).

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 zero-parameter reporting tool, the description is reasonably complete about what information is returned (counts by pack and kind, disk size). However, lacking an output schema and any guidance on how 'pack' and 'kind' are defined relative to siblings like 'breakdown' or 'sources' leaves ambiguity in a toolset with several aggregation options.

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?

With 0 parameters (100% schema coverage trivially) and no params to document, the baseline of 4 applies. The description appropriately describes what the output reveals since there are no input parameters requiring explanation.

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 'What is loaded: counts by pack and by kind, size on disk' states what the tool reports on (loaded corpus, counts, size), giving reasonable purpose clarity. However, it lacks a clear verb-resource structure and doesn't differentiate from siblings like 'breakdown' or 'sources' which could plausibly return similar aggregate data.

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 siblings. Given siblings like 'breakdown', 'sources', and 'style_pack', the agent has no way to know which aggregation tool to choose. The description gives no context about scenarios where 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.