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

Annotations already flag a destructive, idempotent, non-read-only mutation, but the description adds real behavioral context beyond them: partial-update semantics ('only the fields you send are changed'), a state gate that extends beyond 'on air' to PREPARING and SCHEDULED, and the side effect that title/description edits propagate to destination platforms. That is exactly the kind of state-dependent refusal behavior an agent cannot infer from annotations.

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 semantics (partial update) before the state constraints, then alternatives. Every sentence carries a distinct rule; nothing is restated from the schema verbatim.

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 9-parameter mutation tool with nested objects and no output schema, the description covers partial updates, state-gated fields, side effects and sibling alternatives well. It does not mention auth/permission requirements or the failure mode for an invalid projectId, which keeps it short of perfect.

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% and the schema itself already labels several fields as refused while live or scheduled, so the baseline is 3. The description still adds value by widening the refusal window to PREPARING/SCHEDULED and by naming youtubeAdvancedSettings, which does not appear in the schema properties at all.

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+resource (change the settings of an existing project) that cleanly separates it from livereacting_create_project, livereacting_get_project and livereacting_set_playlist. An agent can route to it 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 names alternatives and the conditions that select them: stop with livereacting_stop_stream or cancel with livereacting_cancel_schedules before touching the five refused fields, and use livereacting_set_playlist for playlist changes. It also states which fields are safe to change at any time.

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