Read a draft

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description adds genuinely useful behavior: the default return format is markdown and why that matters for editing, plus when to ask for prosemirror. It does not discuss permissions or publication resolution, which is a minor gap.

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, zero filler, front-loaded with what the tool returns and why. Each sentence earns its place by covering purpose, default behavior, and escape hatch.

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 3-parameter read tool with full schema coverage and no output schema, the description covers the one thing the schema cannot: the roundtrip editing workflow that motivates the markdown default. Only minor gap is no mention of publication scoping behavior or error cases.

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 100%, so all three parameters are already documented, including the markdown-editability vs prosemirror-exactness tradeoff. The description adds workflow meaning on top by tying markdown output to feeding update_draft, which is value beyond the schema text.

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?

States a specific verb+resource with explicit scope: 'Read one draft in full.' The singular 'one draft' distinguishes it from list_drafts and the mention of update_draft frames it as the read half of a read/write pair, so an agent can place it against siblings without opening schemas.

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 roundtrip framing ('edit a sentence and send it straight back to update_draft') tells the agent when this tool is the right entry point, and 'ask for prosemirror if you need the raw document' gives selection guidance for the format option. It lacks explicit when-not/exclusion language, keeping it at 4 rather than 5.

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