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

Annotations already mark this readOnlyHint, idempotentHint, and destructiveHint=false. The description adds non-obvious behavioral context: wait blocks until terminal or budget expiry, polls may need repeated calls, and the caller must reuse the same workspaceId and environment. It also links to output format documentation, which is useful beyond structured fields.

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?

The description is front-loaded with the primary purpose, then covers the polling behavior, error handling, and documentation link in a compact set of sentences. Every clause earns its place and no content is wasted.

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 read-only polling tool, the description covers state retrieval, wait semantics, repeated polling, error recovery, and points to detailed output documentation. With a full output schema present and annotations already declaring safety, nothing essential 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 description coverage is 100%, so the baseline is 3. The description adds extra parameter-related nuance by saying the caller must reuse the same workspaceId and environment when resuming, and warns against re-submitting the document. It does not repeat the schema text, which is appropriate.

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?

The description states a specific verb and resource: 'Get the state and output of an extract run (extract group)' and immediately clarifies the two main use cases: resuming a running run or inspecting a failed one. This clearly differentiates it from extraction-related siblings like run_extract_batch or cancel_extract_run.

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 description gives explicit when-to and when-not-to guidance: call again with wait: true while status is 'running', never re-submit the document, and on UNAUTHORIZED or NOT_FOUND call get_me. It also names get_me as a recovery path, which counts as an alternative.

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