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

Annotations already declare read-only, idempotent, and non-destructive, and the description adds meaningful context beyond them: wait-budget expiry, repeated polling advice, workspace/environment consistency, the 'never re-submit' rule, and error-recovery behavior. No contradiction with annotations.

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?

Four dense sentences, front-loaded with purpose and status scope. Every sentence earns its place: polling behavior, resubmission warning, error handling, and documentation link. No filler or redundancy.

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 is declared, so return values need no explanation. The description covers retrieval, blocking semantics, polling protocol, error handling, and a documentation reference — everything an agent needs to call this tool correctly is present.

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 100%, so the schema fully documents all six parameters. The description reinforces the wait behavior and polling loop but adds little new parameter-level meaning beyond what the schema already states; this matches the baseline for complete schema coverage.

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 ('Get the state and output of a split run') and clarifies its role via 'resume a status: "running" run or inspect a failed one.' This distinguishes it from cancel/delete/list/batch siblings without needing to open 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?

Provides clear usage context: wait:true blocks until terminal, call again with wait:true while running, never re-submit the document, and re-call get_me on UNAUTHORIZED/NOT_FOUND. It does not explicitly name sibling alternatives, but the polling/inspection context is clear enough for an agent to select this tool.

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