get_task

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

There are no annotations, so the description carries the full behavioral burden. It does disclose return content (status plus latest result payload) and, via "latest," hints the value evolves over time, but omits key traits for an async poll: whether results are only present once complete, typical polling cadence, and error behavior for unknown task ids.

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?

A single sentence that front-loads the returned artifacts (status, result payload) with no filler. Nothing could be trimmed 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 two-parameter tool with 100% schema coverage this is close to adequate, and the description partially compensates for the absent output schema by naming the return contents. It still lacks the status vocabulary and completion semantics an agent needs to interpret responses correctly during polling.

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 100% – both task_id and action (with its enum) are documented in the schema, and the enum values map to the sibling creation endpoints. The description adds no parameter-level detail beyond the schema, so the 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?

The description gives a specific verb ("Fetch") and resource ("current status and latest result payload for a seedream task"), so the operation is unambiguous. It does not, however, explicitly connect itself to its sibling async-creation tools (decompose_layers, edit_image, text_to_image), leaving the caller to infer the create-then-poll relationship.

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?

Usage is only implied: an agent can infer this polls a task created by a sibling endpoint, but the description never states when to call it (e.g., after a create call, or repeatedly until completion), nor does it name an alternative or exclusion. No explicit guidance is provided, so 3 is the ceiling.

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