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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuine context beyond that: the result set is workspace-scoped, it flags the location the current site manages, and it warns that names are unreliable identifiers. It stops short of describing the returned 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?

Two short sentences, no filler, with what is returned stated first and the selection constraint second. Every clause carries actionable 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 two-parameter, fully described read tool with no output schema, the description conveys scope, the site-relevance marker, and the identifier to use downstream — enough to invoke it correctly. A brief hint at the returned fields (e.g. ids and names per location) would close the last gap.

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 100%, so site_id and user_goal are already documented, and the baseline is 3. The description adds a rule about connection_id, which is not a parameter of this tool at all — useful for the next step but slightly off-target for this call's inputs.

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 resource (Google business locations connected to this workspace) and adds scope ('which one this site manages'), which is enough to distinguish it from siblings like choose_google_location or get_google_profile. The verb is only implied ('Every ... location'), but the meaning is unambiguous.

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 gives a strong selection rule for the downstream step ('Choose by connection_id, never by matching a name') but never says when to call this tool versus alternatives such as get_google_profile or choose_google_location. Usage is only implied by the phrase 'every ... connected'.

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