start_run

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

No annotations are provided, so the description carries the full burden and does so well: it discloses background execution, the refusal of paths outside the working directory and of secret/credential-denylisted material, and the failure contract (started:false plus exit code and log tail). It does not cover permission/auth prerequisites or concurrency, keeping it short of a 5.

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?

Purpose and return contract are front-loaded, followed by the parameter caveats in roughly priority order. Dense but nearly every clause carries information; a few of the path examples could be trimmed.

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?

For a 10-parameter mutation/execution tool with no annotations and no output schema, the description supplies the return contract and the key path/naming rules. The undisclosed parameters are documented in the schema, so nothing critical is missing, though the interaction between the gate/allow flags and the refusals could be tightened.

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 only 60%, and the description compensates by clarifying the most error-prone parameter – 'chain is a chain name as list_chains shows it (never a path)' – and by grouping task/draft/context/from_run as working-directory-relative paths with examples. It adds no meaning for max_usd, pii_gate, allow_unfenced or allow_secret_shaped, which are left to the schema.

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?

States a specific verb and resource ('Start a harness run in the background') and immediately distinguishes the outcome shape (run id to poll vs started:false with exit code and log tail). An agent can tell it apart from dry_run, resume_run, and run_status without opening any schema.

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?

Routes the agent to run_status for polling and to list_chains for chain naming, and gives a concrete usage recipe ('draft + from_run + rounds=1 makes a panel-only grading pass'). It stops short of naming explicit alternatives/exclusions for the other siblings (dry_run, resume_run), so it does not reach a 5.

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