create_job_run

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

Annotations only supply destructiveHint=false, so the description carries most of the load and does so well: it discloses non-blocking async semantics, that the return is the run's current state, and the confirmed body wrapper key {'job_run': {...}} rather than {'run': {...}}. The EXPERIMENTAL / unverified-origin warning is valuable honesty an agent cannot get from structured fields; it stops short of 5 by omitting auth or quota expectations.

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-loaded with the EXPERIMENTAL caveat, then endpoint, then semantics — a sensible order, and the whole thing is only a few lines. The reference to 'spec/03-conventions.md' is not actionable for an agent and the parenthetical about the wrapper key is slightly tortuous, which keeps it at 4.

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 3-parameter create tool with no output schema, the description covers timing, return shape at a high level, and follow-up polling, which is the critical behaviour. The remaining hole is substantive: a fully undocumented 'configuration' object leaves the agent guessing at the payload, and no mention of auth or project scoping is made.

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?

With 0% schema coverage the description must compensate, and it partially does: the URL template maps {id} to job_id and shows project_id as a query parameter. However, the 'configuration' parameter is never named — the body wrapper hint implies it but the agent must infer that configuration becomes the job_run payload, and nothing says what fields it accepts.

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 concrete verb+resource ('create job run') by naming the underlying endpoint, and distinguishes itself from the read/poll siblings by pointing to get_job_run and list_job_runs. The 'EXPERIMENTAL' framing is a caveat, not a substitute for purpose, but the purpose is still unambiguous.

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?

Explicitly says the call returns immediately and does not block, then names the two follow-up tools to poll — that resolves the main 'what do I do next' question an agent has. It gives no when-not or prerequisite guidance (e.g., permissions, project scope), which keeps it short of a 5.

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