List Reports

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds useful context about persistence — every scan is stored to .argus/runs/ as JSON, Markdown, and HTML — which orients the agent to where data lives without contradicting the read-only annotations. It does not disclose richer behavior (e.g., ordering or pagination), but for a read-only listing the annotations carry the main burden.

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?

Two sentences with the core listing purpose front-loaded and the return fields specified up front. The second sentence adds the persistence-location context without redundancy relative to the schema or annotations. Efficient and well-structured, though the storage detail is slightly tangential to the tool's call semantics.

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?

This is a low-complexity tool: 2 parameters (1 required), no nested objects, no output schema, and strong annotations. The description states the return fields, so the absence of an output schema is not a gap. It is complete enough for an agent to call correctly, with the only minor omission being explicit guidance on which sibling to prefer for related operations.

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 100%: path is documented as the absolute repository root and tool as a filter with an example. The description mentions 'tool' as one of the returned fields, which parallels the filter concept but adds no new parameter information beyond the schema. Per the baseline for full schema coverage, a 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 uses a specific verb-resource pair ('List every recorded ARGUS run for this repository') and enumerates the exact returned fields (run id, tool, date, git commit), making the operation unambiguous. It is clearly a pure enumeration, distinct from analysis operations. However, it does not explicitly name sibling differentiators such as compare_reports or open_dashboard, so sibling distinction is implicit rather than stated.

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 purpose statement implies the usage — call this when you want to enumerate all recorded runs for a repository. But no explicit alternatives or exclusion conditions are given. With roughly five dozen siblings including compare_reports, open_dashboard, and track_run, explicit routing would materially help an agent select between them.

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