shell_exec

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

With no annotations, the description carries the burden of behavioral disclosure. It acknowledges arbitrary execution, suggesting broad power, but does not mention side effects, destructive potential, return values, error behavior, or timeout implications. The guardrail sentence is a usage rule, not a disclosure of what happens when the command runs.

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, each earning its place: the action, the intended use case, and the explicit guardrails. It is front-loaded and compact with no redundant filler.

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?

The description covers purpose and usage boundaries well, but with no output schema it does not state what the agent should expect back (stdout/stderr, exit codes, errors). It also does not disclose side-effect risks beyond the vague inference from 'arbitrary,' which is notable for a shell execution tool.

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 100%, so parameters are already documented with defaults and constraints. The description adds no extra parameter-level meaning beyond describing commands as 'arbitrary shell commands,' which aligns with the schema's 'command' field. Baseline 3 is appropriate.

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 names a specific action ('Execute arbitrary shell commands') and a target ('Termux device'), and frames its intended use as 'direct filesystem inspection and diagnostics.' It does not explicitly distinguish itself from sibling file tools, but the verb and resource are clear enough for an agent to understand what shell_exec does.

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?

Strong guardrails are present: 'Only call when the user has explicitly requested execution, or when diagnostics are clearly required' and 'Do not use for speculative exploration or as a default first step.' It does not name alternative tools like file_read for inspection, so it misses the explicit-alternatives element of a top score.

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