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

With no annotations, the description carries the full burden and does well: it discloses the prerequisite, the exactly-once/idempotency expectation, that the result is handle-only (never inline TS when a handle exists), and the no-polling constraint. It stops short of stating what happens if called before completion or whether repeated calls error, which a mutation-adjacent consume step would benefit from.

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?

Front-loads the tier/mirror identity and the trigger condition, then layers prerequisite, return shape, and follow-up routing. Dense and jargon-heavy ('ts_handle', '_meta.next_action') but every sentence carries operational information; nothing is redundant.

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 values need not be fully spelled out, yet the description still characterizes the return as the originating tool's terminal handle-only result. Combined with the workflow preconditions and post-conditions, an agent has everything needed to invoke it correctly at the right moment.

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 0%, so the description must compensate for the single task_id parameter, and it does: it specifies the value is the task_id from the completed Task returned by tasks_get, and an alternative reuse of the same task_id as job_id. It does not state behavior for an invalid or incomplete task_id.

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+resource — retrieving the terminal result of a completed Task — and explicitly frames it as the tool-only mirror of native tasks/result. It is clearly distinguishable from siblings tasks_get (which produces the status this tool consumes) and tasks_cancel.

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 precise invocation conditions: call exactly once after tasks_get returns status=completed and _meta.next_action=consume_result, and do not poll while working. It also routes follow-up work (pass ts_handle or task_id as job_id to analyze with explicit tal_ids) and forbids the wrong recovery path (never resubmit a build on an Analyze lookup error).

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