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

readOnlyHint=true already covers the safety profile, and the description goes well beyond it by disclosing the payload's role: invariants that must be honored, platform-owned parts with snippet and rationale, and per-file base_hash needed for patching. It also surfaces the draft-vs-live state model and the no-whole-file-regeneration rule, none of which is derivable from annotations or schema.

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 single most important constraint — call before any write — is placed first, and the long enumeration that follows is a dense but purposeful payload manifest. Every listed item corresponds to something a writing agent must honor, so nothing reads as filler.

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?

There is no output schema, so the description must carry the return-value burden, and it does so item by item. Combined with the edit rules and the draft/publish lifecycle, an agent has enough to call this correctly and act on the result without further discovery.

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 only parameter, slug, has 0% schema description coverage and the description never explains it. An agent must infer whether slug identifies a site, a page, or a draft context, and where to obtain a valid one (presumably list_sites). With the schema carrying no semantic load, the description should have compensated and does not.

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 and resource, then enumerates exactly what comes back: notes, brand tokens, page inventory, invariants, platform-owned snippets, per-file base_hash, and edit rules. That enumeration is what separates it from get_site, list_site_files, and read_site_file, which an agent can infer without opening their 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?

Opens with an imperative 'CALL THIS BEFORE ANY WRITE', which is an explicit when-to-call trigger. It also names the downstream alternatives and their constraints ('patch, never regenerate a whole file', 'writes land in the draft; publish_site goes live'), so the agent knows not just when to call this but which sibling to use next.

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