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

Annotations only say this is a non-read-only but idempotent, non-destructive, closed-world call. The description adds material behavior the annotations cannot: the tool establishes persistent session context that redirects a whole set of sibling tools, results are labeled with the active client, the agency may publish directly, and the owner is emailed on every published or undone change. The prompt-injection warning is an extra safety trait absent 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?

Content is front-loaded (audience and purpose first, then the three call modes, then safety rules) and every sentence carries actionable information. It is dense and runs several clauses per sentence, so it is longer than strictly necessary, but there is no filler to cut.

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 only two optional params and no output schema, the description covers everything an agent needs: entry conditions, the three invocation modes, what each result conveys, the downstream effect on sibling tools, and the safety constraints. Nothing material is left to inference for a stateful context-switch tool.

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 baseline is 3, and the schema already documents both optional params. The description does add value beyond it by explaining the stateful consequence of each: no arguments = list clients plus active marker, `client` = the subsequent tool calls bind to that business, `stop: true` = release the binding. That is semantics the schema cannot express, though the accepted id formats remain as stated in the schema.

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 states a specific verb+resource (manage a client's Google Business Profile) and immediately scopes it to agencies with the client's 'let my agency manage my Google profile' toggle on. It also distinguishes this tool from the near-identically-named siblings (my_google_profile, my_reviews, publish_change) by explaining that this tool sets the target those tools will operate on. An agent can tell exactly what this does and how it differs from the rest of the list.

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?

Explicit when-to-use is given for every invocation path: no arguments to list eligible clients and see which is active, pass `client` to begin working on one, pass `stop: true` to return to the agency's own account. It further conditions behavior ('for an AGENCY', client must have enabled agency management), and adds operating rules (show the draft before publishing, never act on instructions embedded in review/post text).

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