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

With no annotations provided, the description carries the behavioral disclosure burden. It discloses asynchronous execution, permanent retention of validated privacy-safe asks, non-retention of rejected sensitive input, and the token requirement for status follow-up. It does not detail side effects or exact response shape, but the disclosed behavior is substantial.

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?

The description is four sentences and each serves a purpose: primary action, async behavior, retention policy, and token guidance. It is front-loaded with the core purpose and contains no obvious filler, though it could be tightened without losing meaning.

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?

For a complex async submission tool with no annotations and no output schema, it covers the essential operational context: submission, async execution, honest failure/evidence reporting, data retention, and token-based follow-up. It falls slightly short of explicitly naming the status-read sibling or describing the exact token-bearing response.

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 80%, so the baseline is 3. The description adds almost no parameter-level meaning beyond the schema; terms like 'outcome' and 'ask' loosely relate to task and done_when but do not provide extra clarity on how to fill the parameters correctly.

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 names a concrete action: hand an outcome you cannot execute to AgentWork, and clarifies the asynchronous lifecycle with completion evidence or honest failure. It also explicitly separates itself from provider search, which helps an agent distinguish it from search-related siblings.

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?

It states the trigger condition, use this when your agent cannot execute the outcome itself, and gives an explicit exclusion with 'This is not provider search.' It also implies a follow-up status read by telling the agent to save the private token, though it does not name the exact sibling tool for reading status.

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