Send your turn to the council

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

Annotations declare a non-read-only, open-world, non-idempotent, non-destructive write, and the description adds behavioral context beyond that: the call blocks waiting for the next step, it can exceed ~50 s and must then be abandoned for council_result, and the text is forwarded verbatim to the other model. It also discloses the 'not waiting for you' response path rather than hiding it.

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 consequence, and every clause carries information (prerequisite, verbatim passing, error path, timeout path). The final sentence chains three conditional clauses, making it denser than ideal, but nothing is wasted.

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?

An output schema exists, so return values need not be described, and the description still covers the prerequisites, the blocking/timeout behavior, and the not-waiting error path. Nothing an agent needs to invoke this 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 coverage is 100%, so the baseline is 3, but the description adds real meaning about `text`: it is passed to the other model as written, so the caller must compose the complete reply rather than a fragment. `council_id` is also implicitly sourced from the message being replied to, matching the schema.

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 your reply to the council's latest message) and scopes it to councils started with council_join, which separates it from council_ask/council_debate siblings. An agent can identify the tool and its role in the turn cycle without opening the 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 call it (after council_join, council_turn or council_result returned your turn) and when not to (only for councils started with council_join). It also names the fallback: if the council is not waiting, call council_result, and repeats that routing when the wait exceeds ~50 s.

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