run_command

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

There are no annotations, so the description carries the burden of disclosing behavior. It does so well by noting the command is just sent as text plus Enter and that run_command does not wait for completion. It could add more on side effects, pane validity, or failure modes, but the no-wait disambiguation is the most important behavior and is present.

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 wording is compact and front-loaded: action, target, then parameter examples, then non-block behavior and follow-up. There is no filler or repeated schema information.

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?

For a tool with only two parameters and an output schema, the description covers invocation semantics, parameter formats, async behavior, and next steps. Any remaining return-value detail belongs to the output schema, so this is materially complete for agent call selection.

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 must compensate, and it does: pane is given a concrete id format such as w17:p1, and command is explained as argv-style words with the example ["git", "status"]. Both required parameters are covered with format and intent.

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 opening sentence clearly names the verb, resource, and semantics: 'Run a shell command in a pane (sends the command text and Enter).' It also distinguishes the tool from waiting/reading tools by explicitly stating that it does not wait and pointing to wait_for_output or read_pane as follow-ups.

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 explicitly tells the agent to use wait_for_output or read_pane afterwards, which is clear behavioral guidance. However, it never contrasts this tool with sibling tools send_text or send_keys, so it stops short of fully explaining when shell execution is preferable to raw text input.

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