exec_run

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

Annotations already include destructiveHint=true, but the description adds non-interactive/no-shell behavior, exclusive lease requirement, cwd restriction, and production write gating via CODEAGENT_*_WRITE + project policy. This goes beyond annotations and gives useful behavioral context.

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 with a clear structure: purpose first, then constraints, then usage guidance. Every sentence adds value with no filler or 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?

Covers purpose, prerequisites (lease), usage context, and key constraints (cwd, write gating). Output schema handles return details. Minor gap is the lack of explanation for optional parameters, but overall the description is sufficiently complete for correct selection and invocation.

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 0%, so the description must compensate. It clarifies command as an argv list (no shell), lease_id as exclusive lease from workspace_acquire, and cwd must stay under project root. However, env_overrides, timeout_s, and max_output_bytes are not explained, leaving a gap.

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 states 'Run a non-interactive command as an argv list (no shell)', which is a specific verb+resource+mode. It clearly distinguishes from terminal_* interactive PTY tools, making the tool's purpose unambiguous.

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?

Explicitly says 'Use for pytest/builds/scripts; use terminal_* later for interactive PTY', providing direct when-to-use and alternative guidance. Also notes the lease prerequisite and cwd constraint, which are essential for correct invocation.

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