run_command

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

No annotations are provided, so the description carries the safety disclosure burden. It explicitly discloses that risky categories (writes, network, git mutations, interpreter one-liners) are delegated to Codex, which 'never full access, no user interruption', and that there is no shell. Missing details about output/error behavior prevent 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?

Four tight sentences: purpose, read-only behavior, risky delegation, and no-shell constraint. Every sentence earns its place, information is front-loaded, and there is zero fluff.

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?

With no output schema and no annotations, the description should state what the tool returns (stdout/stderr, exit codes). It covers safety and execution model but omits return/error details, which is a notable gap for command execution. The project and session_token requirements are documented in the schema, so that gap is less severe.

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 a baseline of 3 applies. The description adds the 'No shell — pass the executable and args separately' guidance, which clarifies how command and args relate and that command is an executable path, not a shell string. This is meaningful extra semantics beyond 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?

The description opens with 'Run a verification command (tests, build, typecheck) in a project' — a specific verb, object, and scope. It distinguishes from sibling file/plan tools by focusing on process execution, and even clarifies the tool can handle risky commands via a delegation path.

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 gives clear context on when to use it: read-only commands run 'directly (free)', while risky commands are delegated to Codex with auto-review approval. It does not explicitly name alternatives or state when not to use it, but the read-only vs risky distinction provides practical routing guidance.

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