tarn_report

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

With no annotations, the description fully communicates that the tool is read-only ('purely reads summary.json + failures.json') and has no side effects (no HTTP, no test execution). It also discloses the input sources, which is sufficient for behavioral understanding.

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 extremely concise—two short sentences—yet packs all essential information: action, output structure, internal operation, and exclusions. Every word adds value, and the main verb is front-loaded.

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 only two optional parameters and no output schema, the description adequately explains the output composition (totals, exit code, grouped failures) and the files read. It could be more specific about the JSON structure, but is sufficient for an agent to decide when to call the tool.

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 detailed descriptions for both parameters (cwd and run_id) with defaults, achieving 100% coverage. The tool description adds no further meaning beyond referencing a 'persisted run', so it meets the baseline of 3 without adding value.

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 identifies the tool's purpose: rendering a concise report (NAZ-404) for a persisted run. It specifies the output format (JSON envelope with totals, exit code, grouped failures) and distinguishes it from other tools by stating 'No HTTP, no test execution' and reading only specific files.

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 context on when to use the tool (for a concise report of a persisted run) and what it does not do (no HTTP, no test execution), implying it is safe and fast. However, it does not explicitly name alternative tools for different use cases, such as tarn_last_failures for detailed failure inspection.

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