run_command

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

No annotations exist, so the description carries full burden. It usefully discloses that output is redacted and compressed and that raw stdout/stderr is suppressed — genuinely valuable behavioral context. But it never discloses that running a command can mutate the filesystem (or its destructive potential), which is a significant omission for a command-execution tool.

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 lean sentences with the core purpose first and the unique return contract second — no filler. It is efficient, though for an 8-parameter tool additional structured detail (e.g., a parameter summary) would have been warranted while still staying concise.

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 complexity (8 parameters, no output schema, no annotations), the description is far from complete. It omits all parameter semantics, expected output structure, and side-effect disclosure, leaving an agent without enough information to invoke the tool correctly beyond the command string.

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% with 8 parameters, and the description explains none of them. It does not clarify cwd, projectRoot, timeoutMs, maxChars, executionKind, taskContextId, or includeStructured. The redaction/compression wording hints at maxChars but never explicitly maps to parameters, so the description fails to compensate for the schema gap.

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?

Description states a specific verb (Run), resource (project-local command), and the return shape (redacted, compressed terminal summary). It explicitly claims raw stdout/stderr never enters the response, which distinguishes it from process-launching siblings and grounds its role as a command gateway.

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 names concrete use cases ('tests, builds, and mutation verification'), giving the agent context on when to invoke it. However, it does not state when NOT to use it or name an alternative tool, so routing against siblings like block_code_mutate or chain_code_stream is left implicit.

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