shell

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

Annotations already declare destructiveHint=true, openWorldHint=true, and non-idempotency, so the agent knows this is an unsafe, side-effecting operation. The description adds only the non-interactive requirement and cwd path constraint; it does not explain permissions, timeout behavior, or what background execution implies, leaving the safety profile to annotations.

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?

A single efficient sentence with the key scoping constraint front-loaded after the verb. It wastes no words, though the terseness is part of the under-specification problem rather than good restraint.

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?

An output schema exists, so return values needn't be described, but for a 9-parameter destructive execution tool the definition is far too thin: no parameter semantics, no usage routing, and no operational context. The definition leaves too much for the agent to infer.

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?

Nine parameters with 0% schema description coverage, yet the description mentions only cwd (and only to require an absolute path). Root, command, args, executable, shell, env, background, and timeout_seconds are completely undocumented in both schema and description.

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: 'Run a non-interactive local command'. The 'non-interactive' qualifier implicitly distinguishes it from run_python and interactive terminal use, but it never names a sibling or explicitly contrasts with the other execution tools.

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 only guidance is the constraint that commands are non-interactive and that cwd must be absolute. There is no statement of when to use this over run_python, apply_patch, or git_* tools, and no exclusion of cases where shell is the wrong choice.

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