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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description goes well beyond them: replace explicitly deletes anything not listed, add is idempotent and skips existing names, descriptions are capped at 300 characters and rejected with the offending name, names are matched loosely across case/Turkish characters/parentheses, and existing prices on untouched services are preserved. It also documents the preview/apply safety gate.

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?

Well front-loaded and structured with bullets and headers, with the action semantics and safety model given prominence. Most sentences earn their place given 0% schema coverage, but the 'Ask Maps AI reads this / worth real visibility' value pitch is promotional framing rather than invocation guidance and could be trimmed.

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?

An output schema exists, so return values needn't be explained, and the description still covers everything else an agent needs for a 4-parameter mutation tool: action semantics, input formats, matching rules, limits, location resolution, and the preview/apply safety gate. Nothing material is left ambiguous for correct invocation.

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 carries the full burden and does: `services` accepts a name list, "Name|description" strings, newline/semicolon strings, or dicts; `action` enumerates all four modes with defaults; `confirm` semantics (preview vs apply); `location` accepts a gbp_list_locations value or business name/domain. Every one of the four raw parameters is documented with accepted formats.

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+resource and scope: it manages the SERVICE LIST on a Google Business Profile, tying it to the exact field name gbp_location_details returns (`services`). No sibling tool in the list covers GBP services, and the description anchors itself to related tools the agent will recognize (gbp_location_details, gbp_list_locations) so the agent can distinguish it immediately.

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 per-action semantics for all four modes: add (default, skips existing), update (description only, adds nothing), remove (deletes by name), replace (list becomes exact, unlisted items deleted). It also states the confirm=false preview-first workflow and the location resolution rule, so the agent knows both when to pick each action and when to preview before applying.

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