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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Read-only. Cannot spend money.' It adds behavioral context beyond annotations by stating that it returns metadata and file list, or file content, which is not covered by the schema. No contradiction.

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, each serving a purpose: first explains the primary use case, second describes the functional behavior, third adds safety and context. It is slightly wordy but front-loads the key usage guidance and remains efficient overall.

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 simple read-only tool with only two parameters and no output schema, the description provides enough information: what the tool does, when to use it, and what it returns. It doesn't detail response format, but for a get operation without an output schema, this is acceptable.

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 50%, and the description compensates by explaining that 'path' returns file content and that without it, the tool returns metadata and file list. The draft_id parameter is self-evident but not explicitly described; the description adds value for the optional parameter.

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 verb 'Get' and the resource 'draft', and specifies exactly what is retrieved (metadata, file list, or file content). It distinguishes itself from siblings like update_draft and list_drafts by emphasizing read-only retrieval and the specific use case of resuming work on a draft.

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?

It explicitly says 'Use this before editing a draft you did not create in this conversation' and 'Use to resume work on a draft from a previous conversation,' giving clear when-to-use guidance. It does not explicitly name alternatives or exclusions, but the context is sufficient to infer that it's for reading drafts, not creating or modifying them.

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