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

The description does real work beyond the annotations: it explains why a "check" call is annotated readOnlyHint=false and destructiveHint=true by disclosing that pending checks "recover and resume stalled work, including its original edits, image retrieval or email send." It still does not say what specifically can be lost or duplicated when a stalled action resumes, but the side-effect disclosure is meaningful.

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 tight sentences, front-loaded with what the tool is, then the side-effect caveat, then the operational rule. Nothing is wasted and the polling instruction lands last where it matters most.

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 carries burden for return values and it leaves "terminal" undefined — an agent is not told what statuses or fields signal completion versus failure. The invocation guidance is complete, but interpreting the response is left to inference.

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 description coverage is 100%, so the requestId reuse rule and sessionToken secrecy are already documented. The description only reinforces requestId reuse ("Pass its original requestId") and gestures at session scoping with "in this session"; it adds little syntax or meaning beyond 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 ("Check a request submitted in this session") and clarifies via the polling line that this is a status/polling operation, not a session listing. It distinguishes itself from get_design_session only implicitly through the requestId/request framing, without naming the sibling.

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 terminal before starting another edit; a queued job is not a completed design" gives clear sequencing guidance, and "Pass its original requestId" tells the caller which identifier to reuse. It does not explicitly contrast the tool with get_design_session or say what to do after a terminal non-success state.

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