tool_usage

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 discloses the persistent data source, the filtering semantics for days, and the 30-day threshold for identifying unused tools. It does not explicitly state that the operation is read-only, but the metric/reporting nature makes that inferable.

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 compact and front-loaded with the metric name and data source. Each clause adds distinct value: source, filtering behavior, and the candidate-for-removal section.

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?

With one optional parameter, no required fields, and an output schema signaled in context, the description covers everything needed to invoke the tool correctly: what data it reads, how days changes results, and what the bottom section represents.

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 description coverage is 0%, so the description fully compensates by explaining the only parameter: days>0 filters to tools called within N days, while days=0 shows the overall top. This is precise and leaves no ambiguity about the parameter's meaning.

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 identifies the tool as a usage metric showing which tools are really called, sourced from persistent tool_usage.json, and even specifies the candidate-for-removal heuristic. It is clear but does not explicitly distinguish itself from siblings such as stats or tool_hint.

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 days>0 and days=0 branches give concrete conditions for different output behavior, and the 'candidates for cutting' section provides a real decision-oriented use case. It does not mention alternatives or when not to use the tool, but the context is otherwise clear.

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