team_send_message

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

With zero annotations, the description carries the full burden, and it does disclose one genuinely non-obvious trait: delivery is live only when the session runs in this process, otherwise the message is merely persisted for audit. It says nothing about failure modes (unknown session_id, invalid workspace_path), whether the send is blocking, or whether a persisted-but-undelivered message can be recovered.

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?

Two sentences, no filler, and the core action is front-loaded before the delivery caveat. Every clause carries information not available in the schema or structured fields.

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 output schema covers return shape, so the description needn't explain responses. But for a 6-parameter write tool with no annotations and 0% schema coverage, it is under-specified: nothing describes required session/workspace semantics, routing via `recipient`, or what happens on an invalid target.

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% across 6 parameters, so the description must compensate. It does valuable work for two of them — enumerating valid `kind` values (the schema declares no enum) and framing `sender` as 'human' or another agent — but leaves `workspace_path`, `session_id`, `recipient` defaults, and body expectations entirely to the field names.

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 gives a concrete verb+resource ("Send a message into a team session") and even names the identity model and message kinds, so the action is unmistakable. It does not, however, position itself against near-neighbours that could plausibly be confused with it (team_report, team_decisions, team_transcript), leaving that differentiation to the reader.

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?

Usage is only implied: the enumerated kinds (question, answer, critique, approval, rejection) hint at when each message form applies, and "as 'human' or another agent" implies the caller-identity context. There is no explicit statement of when to use this tool versus team_transcript, team_report, or team_run_task, and no exclusions.

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