session_send

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

With no annotations provided, the description fully carries the burden and does so admirably. It discloses non-blocking behavior, automatic session creation, queuing of input while Claude is working, the meaning of the `steered` field, and the return structure. This gives the agent a solid mental model beyond the tool's basic function.

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 well-structured: a clear lead sentence, followed by a short creation note, retrieval pointers, and a concise behavioral caveat. It uses emphasis and formatting effectively without wasting words.

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?

The description covers core usage, non-blocking semantics, session creation, and return value shape, making it complete for typical use cases. However, it omits details about optional parameters (beyond a generic 'launch options' grouping), so advanced or configuration-heavy invocations may require external knowledge.

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%, and the description only clarifies `working_dir` ('Set *working_dir* on the first send') and vaguely groups other inputs as 'launch options.' The remaining 10 parameters (e.g., `effort`, `add_dir`, `permission_mode`) are left unexplained, which is a significant gap for a tool with 12 parameters.

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 opens with a specific verb and resource: 'Send *prompt* to a session and return immediately (non-blocking).' It clearly distinguishes itself from sibling tools by noting that no `session_start` is needed and by pointing to `session_wait` and `session_tail` for result collection.

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 states when to use this tool (to send a prompt without blocking) and provides explicit alternatives: 'Call `session_wait` to collect the answer, or `session_tail` to watch progress.' It also explains the mid-flight steering use case and notes that launch options only apply when the session is created, offering clear decision guidance.

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