shell_run

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

The description adds behavioral context beyond annotations: args must be a list (safety), cwd is restricted (security), env keys must be allowlisted (security). Annotations already mark destructiveHint=true, so the description reinforces safety concerns but does not elaborate on return values or error handling.

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?

The description is extremely concise: two sentences without any fluff. It front-loads the core purpose and immediately covers critical constraints. Every sentence adds value.

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 the tool's complexity (shell execution, security, environment) and rich schema (100% coverage, output schema exists), the description covers key constraints. It does not explain success/failure behavior, but output schema likely handles that. Minor missing: no mention of stdout/stderr capture or process lifecycle.

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?

Input schema has 100% coverage with parameter descriptions. The description mostly reiterates schema details (e.g., args never concatenated, env allowlisted). It adds minor clarification for cwd ('locked to project root or subdirectory'). Baseline score of 3 is appropriate as schema already provides adequate meaning.

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 the tool's purpose: 'Run a shell command with arguments as a list (never concatenated).' It specifies the action (run), resource (shell command), and key constraints (args list, cwd locked, env allowlisted). It is distinctive from siblings which are mostly non-shell 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 description provides constraints (args as list, cwd locked, env allowlisted) but does not explicitly state when to use this tool versus alternatives. It implies usage for secure command execution but lacks guidance on when not to use or mention of alternative tools.

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