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

The annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=true, openWorldHint=true), and the description adds genuinely useful behavior the annotations cannot convey: the call suspends durably rather than polling, and it triggers no repeated model calls or new generation. It does not explain why the tool is flagged destructive, whether it can block indefinitely, or what happens on timeout, which leaves a notable gap for a long-running wait.

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, front-loaded with the verb and the artifacts being awaited, with no filler. The dense enumeration of artifact types is long but each item carries distinguishing information, so little is wasted.

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?

An output schema exists, so return-value explanation is not required, and the suspension behavior is covered. However, for a six-parameter, five-required, session-bound tool whose annotations flag it as destructive and open-world, the description says nothing about what must already exist before calling (accepted session bootstrap, catalog version, an initiated work item) or about failure and timeout behavior.

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 only 50%, and the three undocumented parameters (work_id, arguments, request_key) are precisely the ones an agent must supply correctly. The description says 'this turn's exact' work, which loosely implies work_id scoping, but adds no guidance on how work_id, arguments, or request_key relate to each other or how request_key should be chosen for idempotency.

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 gives a specific verb ('wait durably') and a specific scope ('this turn's exact generated tiles, attachments, motion builds and Social drafts'). That scope distinguishes it conceptually from generic siblings like native.wait_for_work or native.wait_for_element_generation, but it never names those siblings, so the differentiation is implicit rather than explicit.

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?

There is no explicit statement of when to call this instead of native.wait_for_work, native.get_work, native.get_run_status, or the narrower wait tools. The phrase 'this turn's exact' hints that it applies to work already initiated in the current turn, but the agent is left to infer the trigger condition and any prerequisites on its own.

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