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

Annotations already mark readOnlyHint=false, but the description goes further by enumerating side effects (updates lastPolledAt, syncs downstream task state, updates logs, delivers webhook) and explicitly listing what it does not do (create work, spend credits, cancel jobs, delete data, change assets). This significantly exceeds the annotation value.

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 description is three sentences, front-loaded with purpose, followed by side-effect boundaries and rate guidance. Every sentence carries essential information with no 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 a tool with side effects and an output schema, the description covers purpose, auth, side effects, exclusions, and polling behavior. It is complete enough for a developer to understand when and how to invoke it correctly, with only a minor gap around explicit sibling alternatives.

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?

The input schema provides thorough descriptions for both parameters (request_id, include_logs), achieving 100% coverage. The description adds no additional parameter-level detail beyond mentioning poll_after_ms, which is not a schema parameter and could be slightly confusing. Baseline 3 is appropriate.

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?

The description opens with 'Poll and sync an existing Cannon Studio generation request by id,' which names a specific verb (poll and sync), resource (generation request), and scope (existing by id). This clearly distinguishes it from sibling tools like create_generation_request by focusing on existing requests.

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?

The description gives clear when-to-use context: for existing requests, with OAuth/API key, and advises polling sparingly with specific intervals. It does not explicitly name an alternative tool as a comparison, so it misses the full 'when-not' guidance, but the context is strong.

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