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

Annotations already say readOnly=false, destructive=false, openWorld=false, but the description adds the substantive behavior the annotations cannot convey: writes land in a separate versioned draft, optimistic concurrency via expected_draft_version, the exact meaning of a 409, per-call and per-file size limits (3 MiB / 100 files / 2 MiB), forbidden path prefixes, idempotency (unchanged: true), and plan-level capacity checks.

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 draft-vs-published distinction and version-conflict rule come first, mechanical limits later. It is longer than ideal for a single paragraph and a few clause chains (adopt, blobs_pending) could be tightened, but nearly every sentence carries operational information.

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, the description correctly spells out the response (new draft_version, manifest_sha256, written/deleted/adopted, blobs_pending and what to do with it). For a 5-parameter mutation tool with concurrency control, it leaves no decision-relevant gap.

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 already 100%, yet the description still adds meaning the schema lacks: path syntax and the admin/, v1/, _sk/ exclusions, the allowed file-type set, adopt's requirement that the target path carry the picture's own extension and that upload_id come from get_draft's candidates, and the semantics of expected_draft_version including the 0-when-no-draft case.

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 concrete verb and resource ("Write pages and files into the site's draft") and immediately scopes the effect with "Nothing is published". It explicitly separates itself from preview_draft, publish_draft, get_draft, and request_upload, so an agent can distinguish it from every nearby sibling without opening a schema.

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 explicit routing: pictures and logos go through request_upload, reading goes through get_draft, showing goes through preview_draft, going live goes through publish_draft. It also states the 409 draft_version_conflict recovery path (re-read get_draft, reapply) and forbids blind resends, plus an explicit consent gate for a mutating tool.

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