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

The two-mode behavior (metadata plus file list, or one file's content when path is supplied) is real behavioral disclosure beyond the annotations. 'Cannot spend money' adds a safety fact the agent cannot infer from readOnlyHint alone, which matters in a toolset containing quote_domain and set_budget. 'Read-only' merely restates readOnlyHint=true, but the rest earns credit.

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 short sentences, front-loaded with the core behavior and mode switch, then usage context, then safety guarantees. No sentence is filler; even the terse 'Read-only. Cannot spend money.' fragments carry signal.

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?

With only two parameters, no nested objects, and no output schema, the description covers mode selection, purpose, and safety adequately. 'Metadata and file list' lightly sketches the return shape. The remaining gap is where draft_id comes from, which is a minor omission for a simple read tool.

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 50%: path is already documented in the schema and the description largely repeats it. draft_id is undocumented in both places; the description implies it identifies the draft but gives no format or sourcing hint (e.g., from list_drafts). Baseline 3 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?

Names a specific verb and resource ('Returns a draft's metadata and file list') and clearly distinguishes the two operating modes via the optional path parameter. It is not confused with list_drafts or update_draft, though it never names a sibling to sharpen the boundary.

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?

'For reading the current text of a draft, including one made in an earlier conversation' gives a clear usage context, including a non-obvious case (drafts from prior conversations). It stops short of stating exclusions or pointing to list_drafts for discovering a draft_id.

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