Job status (optionally wait)

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the behavioral load and does so well: it discloses what is returned (status, progressDetail, result/error), the terminal states for qa_test_this (completed/blocked/unsafe/needs_input), and the timedOut signal from a long poll. Missing is any note on error behavior for an unknown/expired jobId or what happens if the job was cancelled.

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 lead clause is well front-loaded, but the sentence is a single dense parenthetical cramming a field inventory and a state enum list. Since an output schema already exists, much of the 'status, progressDetail, and result/error' enumeration is redundant padding that crowds out more useful content.

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 three-parameter read-only poller with an output schema, the description covers the essential contract: what it returns, how waitMs changes the behavior, and the timeout outcome. It loses points only because the two required identifiers are left unexplained despite the thin schema coverage.

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 coverage is only 33%: waitMs is documented in the schema and merely restated here, while jobId and sessionId have no explanation in either place. The description implies jobId originates from the listed producer tools, but gives no format, no statement of where sessionId comes from, and no indication whether a job outlives its session.

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 pair and resource: 'Poll or wait on a background job', and names the producing tools (qa_test_this, qa_prepare_target, qa_explore, qa_build). It does not distinguish itself from the closely-related siblings qa_status and qa_wait, so an agent still cannot tell from the text alone which of the three to call.

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 implied through the waitMs explanation ('long-polls until the job leaves running'), which tells the agent how to block rather than when to choose this tool. There is no when-not guidance and no routing against qa_status/qa_wait/qa_job_cancel, which are the most likely competing options.

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