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

Annotations only declare the safety profile (read-only, idempotent, non-destructive, closed-world). The description adds the behavioral facts that actually matter here: that long analyses are deferred rather than failing, that polling must continue until "done", the retry interval, and that `result` is byte-for-byte what the original tool would have returned.

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 sentences, front-loaded with the core action, then the lifecycle, then the result guarantee, then the exclusion. Every clause carries operational information; no filler or restatement of the title.

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?

No output schema exists, yet the description covers the return contract itself: the `status` field with its terminal value and the `result` field's equivalence to a direct call. Combined with the polling rules, an agent has everything needed to drive this tool to completion.

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?

Only one parameter at 100% schema coverage, so the schema baseline is 3. The description still adds meaning beyond it by explaining where `jobId` comes from (the deferred response of evaluate, print_check, measure, or check_interference) and that it stays usable across repeated polls.

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 (report/check) and resource (a deferred job handle) and explicitly names the sibling that handles the other deferred case: 'STEP jobs are polled with export_step, not here.' It also names the four tools that produce the handle, so an agent can immediately map the input to its source.

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 the full usage contract: when this tool is produced (slow analysis on a saved project that finishes in the background), the terminating condition (status is "done"), the polling cadence (wait `retryAfterMs` between polls), and the exclusion (STEP jobs go to export_step). Nothing about when or when-not to call it is left to inference.

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