create_discussion

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

Annotations already declare non-read-only, non-idempotent, non-destructive, open-world, so the safety profile is covered. The description adds real value beyond that by listing the returned fields (id, key, url, topic_id) despite there being no output schema, and by noting the '1 call' cost and that omitting private falls back to the group default. It does not explicitly state that recipients are emailed by default (notify_recipients semantics), which the schema carries instead.

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?

A single dense paragraph that front-loads the action, then parameters, then return values, then routing. Every clause carries information; nothing is filler.

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 an 11-parameter mutation tool with no output schema, the description supplies the return fields and the required/optional split, which fills the biggest gap. It is slightly thin on the recipient-notification behavior and permissions/auth needs, but nothing essential for a correct call 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 64% and the description groups parameters into required (title, group_id) and optional, and clarifies description_format usage and the private default. However, most of that repeats defaults already in the schema, and it says only 'recipients' for the four recipient-related parameters (emails, ids, audience, message, notify flag), leaving the notification surface to 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 ('Start a discussion in a group') and immediately scopes it against siblings by naming create_comment as the tool for threading and list_discussions for dedupe. An agent can distinguish this from create_poll or create_comment 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 tells the agent to check list_discussions for duplicates first and to use create_comment to add to an existing thread. That is a clear when-to-use precondition plus named alternatives, which is exactly what routing guidance should look like.

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