push_config_result

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

With no annotations, the description carries the full burden and does it well: it enumerates all seven statuses, maps each to which field carries the payload (diff/result/error), and discloses the failure modes — lock/load errors, failed health checks, and a commit that rolls back after confirm_timeout minutes. It also discloses the 10-minute retention window for finished jobs, which is a real behavioral constraint an agent needs.

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 one-line purpose, then a dense but well-organized status enumeration. It is somewhat run-on and the status list could be a table for faster scanning, but every clause conveys distinct information — nothing is padding.

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?

There is no output schema, so the description must explain return values itself, and it does: it names the fields for each status and reuses the sibling's semantics ('result holds the same text push_config returns'). An agent has enough to interpret every response it could receive.

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 0% for the single job_id parameter, so the description has to compensate — it does, by explaining that a bad or expired id yields 'unknown' and that ids expire 10 minutes after the job finishes, which is exactly the semantics a caller needs. It stops short of saying where job_id comes from (the return of push_config_start), which is the one remaining gap.

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 and resource: fetch a push_config_start / deadline-bound push_config job by id. It distinguishes itself from the sibling push_config_start (which originates a job) and push_config (which performs the push), so an agent can tell which one to call without inspecting schemas.

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?

The status list makes the calling pattern explicit — 'running (keep polling)' tells the agent to re-invoke, and 'done' tells it to stop. However, it never states an alternative for a caller who wants the run to block until completion, nor any polling interval or retry guidance.

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