dry_run_command

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

With no annotations, the description correctly carries the burden and discloses the two most important non-obvious traits: nothing is executed, and a SAFE verdict is heuristic rather than an authorization signal. It omits what happens on malformed input or how ambiguous commands are labeled, but the critical safety caveat is front and center.

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?

Two short sentences, zero waste, with the non-execution guarantee placed first and the safety caveat second.

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-value explanation is fairly excused, and the safety profile is covered. However, for a 2-parameter tool at 0% schema coverage, the total silence on the shell selector and command limits leaves a real gap for correct 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 needed to compensate and does not. Neither the required "command" parameter nor the "shell" enum (bash/sh/pwsh) is mentioned, and there is no default or format guidance for shell selection.

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 precise verb ("Classify") and resource ("shell text") with an explicit scope limit ("without executing it"), so an agent knows this is a static analysis tool, not a runner. The sibling tools (audit_path_access, budget_guard, secret_masker) are unrelated enough that no explicit differentiation is needed.

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?

Use is implied rather than stated: the phrase "not permission to execute" hints this is a pre-flight check before running a command. It never says when to prefer it, what to do with the result, or which tool actually executes the command. No alternatives are named.

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