list_runs

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

With no annotations, the description fully discloses behavior: it is read-only, folds row pairs, applies filters, returns list or aggregate, and handles missing journal gracefully. This is comprehensive and leaves no ambiguity about side effects.

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?

Three sentences, front-loaded with the core identity, then detailed behavior, then edge-case handling. Every sentence adds necessary information without redundancy.

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 10 parameters and no output schema, the description covers almost all relevant aspects: purpose, filters, output modes, and error handling. It lacks explicit description of the return format for the non-aggregate case, but the mention of 'folded list' gives a reasonable hint. Overall, it is sufficient for an AI agent to understand and invoke the tool correctly.

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 0%, so the description must explain parameters. It lists filter parameters (since, limit, agent, verdict, mode, invocation, work_type) and mentions aggregate and trend_days implicitly via 'aggregate bundle' and 'trend sparkline buckets'. It also clarifies default aggregate=false. However, it does not detail workspace_root or the exact format of parameters like since (but schema has enums for some).

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 it is a read tool for `.squad/runs.jsonl`, describes the two-phase folding, and specifies the two output modes (list vs aggregate). The verb 'Read' and resource 'squad/runs.jsonl' provide a specific and distinct purpose.

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 explains that the tool reads runs with filters and can return aggregates. It also notes that missing journal returns empty, not error, which guides usage expectations. However, it does not explicitly differentiate from sibling tools like list_tasks or record_run, which are other read/write tools for different resources.

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