Write stdin

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

Annotations provide no behavioral hints (all false), so the description carries the burden. It discloses the key non-obvious behavior: empty chars poll for output while non-empty chars write to stdin. This is critical for correct invocation and is not evident from the schema. It also provides a concrete example. It does not disclose side effects or limitations like whether writing is blocking, but the main behavioral trait is covered.

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 compact and front-loaded: the purpose is stated first, followed by the critical chars rule and a concrete example. No wasted words. The JSON example is a useful structural aid. Could be considered slightly terse, but 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?

Output schema exists, so return values need no explanation. The core interaction modes are covered, but the description lacks guidance on how command_id relates to exec_command, what verbosity levels mean, and how output limits interplay with polling. For a 6-parameter tool with 0% schema coverage, this leaves gaps an agent must resolve elsewhere.

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 all parameter semantics must come from the description. The description explains 'chars' (empty vs non-empty) and implicitly command_id and yield_time_ms via the example, but verbosity, preview_bytes, and max_output_bytes are left unexplained. Names and defaults give hints, but the description does not add sufficient meaning for these parameters, making correct selection harder.

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 states a clear verb-resource pair: 'poll or interact with a running command by command_id.' It distinguishes from siblings like exec_command (starts) and kill_command (terminates) by focusing on stdin interaction and polling. The empty/non-empty chars rule adds specificity. However, it doesn't explicitly name a sibling alternative, so not a perfect 5.

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?

No explicit guidance on when to use this tool versus read_output or exec_command. The description implies usage via behavior but never states conditions or alternatives. An agent must infer that this is for sending input, not retrieving output. Lacks when-not guidance.

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