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

Annotations only declare the safety profile (not read-only, open-world, non-destructive); the description adds the wait window, the timeout-to-poll fallback, the fact that the agent works on a working copy until applied, and that hosts running tool tasks receive the turn as a task instead. That is substantial behavior beyond the annotations. It stops short of stating cost/rate implications of the message itself or what the raw return structure looks like.

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?

The core action and wait bound are front-loaded, and the response taxonomy follows in a compact enumerated sentence. The final sentence on task-host behavior is dense and slightly cryptic, but it carries real information rather than 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?

With no output schema, the description takes on the burden of describing return values and does so by listing the four possible agent responses and the action each implies. Combined with the timeout/poll guidance, an agent has everything needed to call this correctly from a chat-oriented multi-turn workflow.

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; the description goes further by explaining plan_approved semantically ('answer with plan_approved:true to build it') and tying chat_id to its origin via the start_chat flow. The attachments parameter (≤4 hosted media URLs) is left entirely 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?

Names a specific verb and resource ('Send a message to the Studio agent') and immediately bounds the call with a timing characteristic ('wait (up to ~45s) for its answer'). It also enumerates the possible reply shapes, which lets an agent distinguish this from siblings like apply_turn, get_turn, and app_quote without opening their schemas.

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 routes the agent after each outcome: apply a PROPOSAL with apply_turn, answer a plan with plan_approved:true, and poll get_turn if the turn is still working. These are named alternatives with the conditions that select them, so no downstream decision is left to inference.

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