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

Annotations already establish the safe-read profile (readOnlyHint, idempotentHint, non-destructive, closed-world), so the bar is lower. The description adds genuinely new context: the call is free, and there is a boolean done field to poll against, both of which tell the agent how to behave.

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 short sentences, front-loaded with the cost attribute and the polling condition. Every sentence conveys actionable information with no filler, though the one-word "Free." opener is terse rather than integrated.

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-value documentation is not required, yet the description still flags the done field, which is the key contract for polling. Combined with cost and provenance, it is sufficient for a one-parameter polling tool.

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 0% for the single jobId parameter, so the description must compensate. It does partially by tying the job to llm-chat_v1's creation, implying where to obtain the ID, but never states the expected format or that it is required.

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 resource (status and result of a job) plus the owning tool (llm-chat_v1), which cleanly distinguishes it from the sibling llm-chat_v1 that creates the job. An agent knows exactly what this returns 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?

"Poll until done is true" gives explicit polling guidance tied to the async llm-chat_v1 flow. It implicitly establishes the prerequisite (a job must exist) but never states the call ordering or that a done=false response means retry, so it stops short of full when/when-not guidance.

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