send_message

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

With no annotations supplied, the description carries the full burden and does so well: it discloses that model/thinking changes restart the session in a new tab with full history, that a running turn is interrupted, that an exited process or closed tab causes a resume in a new tab, and that the call is refused during dialogs. These are exactly the destructive/side-effect facts an agent needs before invoking.

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?

Front-loaded with the core action and its two modes, then organized into a parameter section followed by failure/edge-case notes. The 'model / thinking:' pseudo-heading is slightly unconventional but aids scanning, and every sentence contributes a distinct behavioral fact.

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 mutation tool with no annotations, no output schema, and 4 undocumented parameters, the definition covers side effects, interruption, resume-after-exit, and the dialog refusal condition thoroughly. The remaining gap is that it never states what the call returns or how to obtain the target agent's 'name' (e.g., via list_agents), which an agent must know to invoke it correctly.

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 compensate. It explains 'model' and 'thinking' in depth (same values as start_agent, including auto tiers) plus their restart consequence, but it never defines 'name' (presumably the target agent identifier) or what form 'message' should take. Two of four parameters are richly covered; two are left to inference, keeping it below a 5.

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 ('Send a message to an agent as if typed in its tab') and immediately clarifies the two modes: follow-up when idle, steer while working. It implicitly separates itself from press_keys/capture_screen by describing text entry into the agent's own tab, but it never explicitly contrasts with start_agent, so the differentiation is partial rather than crisp.

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?

Gives explicit when-to-use (idle follow-up vs mid-turn steer), an explicit when-not ('Refused while the agent may be showing a dialog (still starting, or Claude Code mid-turn)'), the reason ('typing there could answer the dialog'), and concrete alternatives ('Use capture_screen and press_keys, or wait for the turn to end'). It also advises preferring model/thinking switches while the agent is idle. Nothing about routing is left to inference.

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