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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses the real-world consequence: changes "go live at once" and "whatever is in it is what customers are quoted." It also reveals that draft is rebuilt from sources when they change (so hand-edits can be overwritten) and that lines starting "> Check:" are stripped — behavior an agent could not infer from structured fields.

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 content is dense and earns its place, but it is delivered as one long run-on sentence with deeply nested parentheses, making the field-by-field meaning hard to parse. Splitting the draft/instructions/restore_version details into separate sentences would improve scanability without losing 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?

For a five-parameter mutation tool with no output schema, it covers ownership/auth, all parameters, live-effect semantics, and the required read-then-confirm workflow. It stops short of saying what is returned after a successful save (e.g., a new version id) or what happens on failure, which would round it out.

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 description coverage is 0%, so the description must carry all param meaning, and it largely does: draft is the business brief, instructions are the owner's additions, restore_version is a version id that goes live as a new version, and publish/publish_when_ready are deprecated. Minor gap: it says draft is "about 4,000 characters" while the schema allows 20,000, which could mislead on the actual limit.

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 names a specific verb and resource ("Change the business's AI receptionist") and enumerates exactly which fields are mutable (draft, instructions, restore_version), which clearly separates it from the read-only sibling "receptionist". An agent can tell what this tool does without opening the 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?

It states the trigger ("when the owner wants to teach their AI agent something new, or change what it says"), an explicit prerequisite ("Read receptionist first"), and a required workflow step ("show the owner a brief you wrote before saving it"). It also retires two parameters (publish, publish_when_ready) so the agent does not use them.

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