get_judged

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

With no annotations, the description carries the burden and does disclose the key behavioral trait: the response shape is state-dependent, returning an attempt log while running and adding the best image, pass/fail verdict, and per-attempt scores/problems when done. It omits polling semantics (blocking vs. point-in-time) and any rate-limit or retention notes.

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 front-loaded sentence that enumerates states first, then payloads, with no filler. It reads as a dense run-on, but every clause carries information an agent needs.

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 detailed return-value documentation is not required, yet the description still sketches the payload per state. What's missing is the polling contract (blocking, cadence, terminal-state behavior), which matters for a job-status tool with no annotations.

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?

One required parameter with 0% schema description coverage, so the description must compensate. It implies job_id refers to a run_judged job but never states where that id originates (presumably the run_judged response) or what happens with an unknown/expired 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?

Names a specific verb+resource: fetching status/results of a run_judged job, and enumerates the state space (running | done | error) plus what payload accompanies each state. An agent can tell it apart from run_judged, but the description never distinguishes it from the sibling get_job, which sounds equally like a status poller.

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: the reference to a 'run_judged job' suggests polling after invoking run_judged. There is no explicit 'use this instead of get_job' routing, no statement of when to poll versus when the job is finished, and no guidance on what to do on 'error'.

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