Read draft

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

Annotations already declare readOnlyHint=true, and the description adds real behavioral context: waitSeconds polls for progress mid-build, the tracks view is paged, and the tool 'also resumes an interrupted build' — a side effect beyond a pure read that the annotations do not convey. Return-format details are absent, but the added side-effect disclosure is meaningful.

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?

Dense but front-loaded: the view taxonomy comes first, then wait behavior, then the draftId default. Every clause carries information; the only mild cost is that four views are packed into one long sentence.

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 no output schema and low schema-description coverage, the description does most of the heavy lifting by defining each view's payload and the wait/resume behavior. The gap is pagination semantics (limit/offset ranges and defaults) and what the summary view returns, but overall it is sufficient to call correctly.

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 only 20%, so the description must compensate and does so partially: it explains the view enum semantics, the waitSeconds cap, and the draftId default. It says nothing about limit/offset beyond the word 'paged', leaving pagination behavior half-documented.

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+resource (show a draft) and enumerates the four distinct views, each with a gloss. It also separates itself from edit_draft by noting the tracks view returns 'stable ids for editing' rather than performing edits, so an agent can place it among its siblings.

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 clear conditional guidance: omit draftId for the most recent draft, pass waitSeconds while a draft is building, choose the view by what you need. It stops short of naming alternatives (e.g., list_drafts for enumerating drafts, edit_draft for mutation), so it is strong context without explicit exclusions.

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