dsh_send

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

With no annotations, the description carries the full behavioral burden and largely succeeds: it discloses the async return (run_id), that the turn runs in the background, the queue-vs-inject semantics, per-message run_ids, and the side effect that a non-workspace cwd is registered in the sidebar first. It omits error/permission behavior (e.g. invalid session_id) and any auth requirements, which is the only gap.

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?

Purpose and the session-vs-new distinction are front-loaded, then behavior and the next-step handoff. It is dense and somewhat long, but nearly every clause carries actionable information (verbatim delivery, language guidance, run_id-per-message). Minor tightening possible in the message-authoring advice.

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 complex async dispatch tool with no output schema and no annotations, the description covers what an agent needs: what is returned (run_id), that the turn is backgrounded, how to retrieve the reply (dsh_wait or wait_command), mode selection, and the cwd side effect. Nothing essential to calling it correctly is missing.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema by explaining the role split between session_id (continue) and cwd/workspace_id (new session), including that cwd auto-registers a workspace. The mode/default semantics are largely duplicated from the schema's own descriptions.

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?

Opens with a specific verb+resource ('Send a message to DeepSeek Harness') and immediately disambiguates the two entry modes: continue an existing session via session_id vs. start a new one via cwd/workspace_id. An agent can distinguish this from siblings like dsh_wait or dsh_list_sessions without opening any schema.

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?

Explicitly states when to use which parameter (session_id vs cwd/workspace_id), when to use mode followup vs steer based on whether a session is already working, and names the follow-up tool ('wait for the reply with dsh_wait'). Routing to the next step in the workflow is spelled out.

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