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

Beyond the readOnlyHint/destructiveHint annotations, the description adds important behavioral context: the tool requires deploy:write scope, reports up to 500 files, interprets blobs_missing as files whose bytes did not arrive, distinguishes draft_version from published_version, and explains the null case for live_deploy_id. It also connects the 409 case to re-reading the draft, which is valuable operational guidance.

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?

The description is dense but front-loads the key fact ('Read-only; changes nothing') and then provides a structured enumeration of return fields and usage hooks. The length is justified because there is no output schema, though the single long parenthetical list makes it less scannable than it could be.

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 read-only inspection tool with no output schema, the description is complete: it explains the return fields, their meanings, version relation semantics, missing-blob handling, publish-related identifiers, and when to call the tool. An agent has enough information to invoke get_draft correctly and interpret its results without additional documentation.

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?

There is only one parameter, site, and the schema description already explains it fully as the site ID from list_sites. The description refers to 'the site's draft' but does not add any meaning beyond the schema's parameter documentation, so the baseline of 3 is appropriate for 100% schema coverage.

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 that this tool reads the site's draft and precisely enumerates what the draft response includes: draft_version, files, upload candidates, missing blobs, published_version, live_deploy_id, last_publish, and versions. This is far more specific than a generic 'get draft' and lets an agent distinguish this tool from siblings such as read_draft_file, preview_draft, and list_versions.

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 description gives explicit invocation conditions: call it before the first write_files of a conversation and after any 409. It also explains how the returned values are used by write_files, publish_draft, and restore_draft, which helps an agent understand the tool's place in the workflow, though it does not explicitly state when to prefer alternatives like preview_draft or read_draft_file.

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