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

Annotations only say this is a non-read-only, non-destructive, non-idempotent open-world call. The description adds the crucial semantics: it creates a DRAFT only and nothing on Google changes until a separate publish step, and existing additional phone numbers are preserved rather than overwritten. That is exactly the behavioral context the annotations cannot convey.

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 front-loaded sentences with no filler, and the draft-only constraint lands early. There is mild redundancy between 'confirm every character with the owner' and 'Show the owner the draft this returns, word for word,' which slightly dilutes the otherwise tight structure.

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?

No output schema exists, and the description compensates by telling the agent what comes back (a draft to show the owner verbatim) and what to do with it. Combined with the owner-confirmation workflow, an agent has everything needed to invoke and follow up correctly.

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 the format constraints (area code, https:// prefix) are already documented. The description still adds meaning by clarifying that 'phone' targets the *primary* number while additional numbers are kept, which resolves ambiguity about the scope of that parameter.

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 (draft a change) and specific resources (website and/or primary phone), and distinguishes itself from the many other propose_* siblings by naming the exact listing fields it touches. An agent can immediately tell this apart from propose_attributes, propose_hours, etc.

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?

Names the downstream action explicitly ('publish it with publish_change only after they say yes') and sets the precondition of owner confirmation, which is strong routing. It does not mention discard_change/undo_change as the path when the owner rejects the draft, so the when-not branch is only implied.

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