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

Annotations already signal destructive and idempotent behavior. The description adds valuable specifics: signees not included in the complete signeeDetails list may be removed, and omitting fileId preserves the current file. This goes beyond the annotations and helps the agent understand the destructive nature of a full update.

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?

Three sentences, front-loaded with the core action and the critical status prerequisite. It includes only high-value behavioral warnings and avoids repeating schema content. No filler or unnecessary detail.

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?

Given the tool's complexity, the exhaustive schema carries most of the parameter documentation burden, and the description covers the two high-risk behaviors: signee removal and file preservation. It does not describe return values or error cases, but there is no output schema and the schema's parameter detail is sufficient for correct invocation.

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?

The input schema provides 100% coverage with rich descriptions for every parameter, including nested objects and coordinate systems. The description adds little parameter-level meaning beyond the schema; it reinforces signeeDetails completeness and fileId optionality, but those points are also present in the schema.

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 the action ('Update an existing draft') and the resource, and adds the prerequisite that the draft must still have status draft. It frames the tool as a full draft configuration update, which distinguishes it from create_draft and update_signee without ambiguity.

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 a clear when-to-use condition: the draft must still have status 'draft'. It also conveys that this is a full-update operation, which implies it is the right tool for comprehensive draft edits. However, it does not explicitly mention alternatives like update_signee for single-signee changes or say when not to use this tool.

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