discover_cli

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

With no annotations, the description does add real behavioral context: help prose is downgraded to 'dirty-side evidence' and only confirmed structure is returned, so the agent knows not to trust raw help text. It omits important traits for a tool that must execute a CLI to probe it — whether the command is actually run, side effects, safety, or any permission/auth requirements.

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 tight sentences with the purpose front-loaded and no padding. 'Dirty-side evidence' is slightly jargon-y but earns its place by signaling the trust level of help output.

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 structure need not be spelled out, and the description correctly frames the result. But for a tool that executes an external binary, missing execution semantics and an unexplained second parameter leave meaningful gaps.

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 0%, so the description must carry the parameter burden and does not. 'cmd' is self-evident, but 'takes_files' (boolean, default true) is never explained — the agent cannot tell whether it declares that the target CLI accepts file arguments or whether the tool itself should pass files.

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 ('Discover a CLI's interface') and even describes the shape of the result (options, arity, value types), which is more than most definitions offer. It does not, however, distinguish itself from sibling probe_cli or discover_ui, leaving the agent to infer which discovery tool to pick.

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?

Usage is only implied: the phrase 'help structure confirmed by behavior probes' hints that this is a discovery step feeding later probing, but there is no explicit when-to-use, when-not-to-use, or named alternative among siblings like probe_cli or discover_ui.

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