render_job

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

With no annotations, the description carries the full burden and does so well: it enumerates status values, the exact payload returned per terminal state, that results persist for repeat polls, what discard actually destroys (cached image and temp document), and an auto-eviction policy with oldest-first ordering.

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 action and return contract, then appends lifecycle details in short parenthetical clauses. Every sentence adds information an agent needs; none 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?

No output schema or annotations exist, yet the description specifies the return shape for every branch (running/done/failed), the durability of results, and cleanup semantics. Nothing required to invoke or interpret a poll correctly is missing.

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%, so the description must compensate. It fully explains discard (what it frees, when it is honored vs. ignored) and job_id is implicitly the handle returned by render_photoreal_submit, though it never states the format or where job_id comes from explicitly.

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 (poll) plus the exact resource it polls (an async render started by render_photoreal_submit), naming the sibling that produces the job_id. An agent can tell this apart from job_status/job_result without opening any schema.

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 clear operational guidance: pass discard=True once a terminal result is obtained, and that discard is ignored while running. It doesn't explicitly compare against the other async-status siblings (job_status, job_result), but the pairing with render_photoreal_submit makes the intended context unambiguous.

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