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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real value: it enumerates the four terminal status values and guarantees the poll does not re-execute the underlying operation. It omits whether the call is non-blocking or how often to poll.

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?

Two sentences, zero redundancy, with the operation scope front-loaded and the return-state/non-execution guarantee second. Nothing can be cut without losing information.

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 compensates by listing the possible returned statuses, and it pairs well with the safety annotations for a single-param read. It leaves edge behavior (unknown or expired request_id, blocking vs non-blocking) unaddressed.

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% and the request_id property description is thorough, so the schema carries the parameter burden. The description only reinforces that request_id identifies the pending operation across all three operation types; 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?

Names a specific verb (poll) and the exact resource types it covers: long Blender commands, background renders, and screenshots, keyed by request_id. It is implicitly distinct from the mutation siblings like cancel_blender_operation, though it never explicitly names a sibling to contrast with.

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 mention of 'long Blender command, background render or screenshot' implies usage after kicking off an async operation, but it never states the trigger condition, polling cadence, or when to use cancel_blender_operation instead. Usage is inferable rather than spelled out.

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