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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds genuinely new operational context: the repeated-polling requirement, the guarantee that nothing is scheduled until the writer acts, and how an unanswerable question surfaces via failureMessage. That is well beyond what the structured fields convey.

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?

Purpose is front-loaded, then polling behavior, then output interpretation. Every clause carries distinct information (cadence, stop condition, no-side-effect guarantee, failure channel) 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?

Even though an output schema exists (so return values need not be explained), the description supplies the interpretive frame — what done, answer, noteIdeas and failureMessage mean for the caller's next action. Nothing needed to invoke and act on this tool is missing.

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 runId's provenance and workspace's account-selection semantics are already documented in the schema. The description only alludes to runId indirectly and says nothing extra about workspace, so it does not add meaning beyond the schema — baseline 3 applies.

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 on a Research Desk question') and ties it to the exact originating tool, start_research_desk_question, so it is unmistakable against the many other get_* siblings. The polling nature of the tool is clear from the first sentence.

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?

Gives an explicit polling cadence (every 10 to 20 seconds), the loop exit condition (done becomes true), and an explicit exclusion ('do not start a new question meanwhile'). This is exactly the when/when-not guidance an agent needs for an async job.

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