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

Annotations already declare readOnlyHint and destructiveHint=false, yet the description adds real behavior: only agent-settable fields are returned and other saved page content is omitted, plus the permission scope and the sign-in prompt on unconnected accounts. The prompt-injection disclaimer is useful safety framing but is largely boilerplate shared across this server.

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?

Front-loaded with the action and the returned-data scope before auth details, and every sentence maps to a distinct concern. It runs slightly long because the site-content-as-data warning reads as server-wide boilerplate rather than tool-specific guidance.

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 single-record read with one required param and no output schema, the description covers scope, auth, and partial-return behavior adequately. The remaining gap is that it doesn't indicate which posting fields come back, leaving the agent to discover the shape at call time.

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 single `id` parameter is fully documented in the schema, including its provenance (GET /me/drafts). The description adds no further meaning about the id itself, so with 100% schema coverage the baseline of 3 applies.

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?

Opens with a specific verb and resource ("Read one Post Work draft") and immediately scopes the payload to "one draft and its posting fields." That clearly separates it from list_my_drafts and from mutation siblings like update_work_draft, though it never names an alternative explicitly.

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?

Gives prerequisites rather than routing: it names the required permission scope (work:read) and the sign-in fallback when the member hasn't connected. It does not say when to prefer this over preview_my_draft or list_my_drafts, so usage is implied rather than stated.

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