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

Annotations already declare readOnlyHint, destructiveHint, and idempotentHint, covering safety. The description adds valuable context: waiting semantics, absence of a list endpoint, and error handling (re-calling get_me). It does not contradict annotations and enriches understanding of runtime behavior.

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 information-dense yet well organized: primary purpose first, then waiting behavior, then workflow-specific caveats, then error handling, then doc reference. Every sentence earns its place without 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?

For a read-only, idempotent operation with full schema coverage and annotations, the description covers all necessary aspects: what to do, when to use it, waiting semantics, error recovery, and where to find output shape. No critical information 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 100%, so parameters are fully documented. The description adds practical meaning: 'keep the run ID' because no list endpoint exists, and 'must match a granted target from get_me' for environment and workspace. This goes beyond schema descriptions.

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 clearly states it retrieves the state and output of a form detection run, with specific verbs 'Get' and options to 'wait'. It distinguishes from siblings by noting there's no list endpoint and that it's the companion to detect_form_fields, so an agent can easily differentiate it.

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 explicit when-to-use guidance: resume running runs, inspect failed ones, use wait:true to block, and re-call until terminal. It also warns against re-submitting the document and instructs to re-call get_me on errors, giving clear decision rules.

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