evidence_index

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

Even without annotations, the description effectively communicates the tool's behavior: it scans a directory, groups data by runId, and returns a timeline with metrics. It also discloses that filtering by runId and including traceIds is optional. The description is transparent about the read-only nature (no mention of side effects), though it could explicitly state that no modifications occur.

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, using only a few sentences to convey the core purpose, parameters, and output metrics. It is front-loaded with the main action and avoids any extraneous information. Every sentence earns its place.

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 two optional parameters and no output schema, the description provides a good overview of the output: a timeline with key metrics like traceId, error count, API response count, and data diff count. While it does not detail the exact output structure, it provides enough context for an agent to understand the tool's purpose and expected results.

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%, so the schema already documents both parameters. The description adds context by explaining that runId filters the timeline and includeTraceIds controls trace ID inclusion. However, it largely restates the schema descriptions, providing marginal additional value. 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 scans evidence.json files in the reports directory, groups by runId to generate a validation timeline, and aggregates key metrics. It is specific about the verb (index/scan), resource (evidence files), and outcome. However, it does not explicitly differentiate from sibling tools like 'evidence' or 'evidence_pack', which might have overlapping functionality.

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 for cross-step and cross-runId retrieval, but it does not provide explicit guidance on when to use this tool versus alternatives. Sibling tools like 'evidence' and 'evidence_pack' exist, yet no usage boundaries or exclusions are mentioned.

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