agy_discussion_turn

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

Goes meaningfully beyond annotations: failure/cancellation consumes an attempt, there are no automatic turns or retries, and it may incur cost and CLI side effects. These are exactly the operational caveats annotations like openWorldHint and idempotentHint cannot convey. It stops short of saying how many attempts exist or what the side effects touch.

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?

Three tight sentences with no filler; the core action leads and the behavioral caveats follow in priority order. Every clause carries distinct information.

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?

Behavioral risk is well covered, but for a 6-parameter, non-idempotent, open-world tool with no output schema and zero schema descriptions, an agent still cannot tell what model/channel/reply_to/participant mean or what a turn returns. The definition is adequate on behavior and incomplete on interface.

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% for 6 parameters, and the description only clarifies that 'instruction' is optional. model, channel, reply_to, participant, and discussion_id are entirely undocumented anywhere, so the description fails to compensate for the coverage gap.

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?

'Yield ONE authorized peer turn' names a concrete action and its unit (a single turn), which separates it from agy_discussion_read or agy_discussion_note. The phrasing is abstract jargon ('authorized peer turn', 'bounded shared context'), but the resource (a peer discussion turn) is identifiable.

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?

'Instruction is optional; the peer may initiate questions or proposals, including the first turn' hints at when instruction is needed and that the first turn can originate from the peer. However, it never states when to choose this over agy_run, agy_council_round, or agy_discussion_recover, so routing still requires inference.

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