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

Consistent with readOnlyHint=true. Beyond the annotations it discloses the defaulting behavior when both identifiers are omitted and specifies that pronoun_mode and approved_facts are returned when set and empty otherwise, which is real behavioral context an agent cannot get from the schema.

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 tight sentences, front-loaded with the purpose before the parameter rules. The trailing clause "— the account-aware check_brand_voice guidance" is grammatically murky and slightly obscures why those fields are returned, the only real waste in the text.

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 no output schema, the description takes on return-value explanation and covers the two conditional fields plus the empty case, which is the right call. It leaves the main payload of the brand voice record itself implicit, but for a two-parameter read tool the coverage is close to sufficient.

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 0%, so the description must carry the load, and it does: it explains that domain and site_id are alternative targeting keys and that omission resolves to the auth default. It does not clarify precedence if both are supplied or the expected domain format (hostname vs full URL), leaving one ambiguity.

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?

"Get canonical brand voice for the site" gives a specific verb and resource, and the canonical qualifier distinguishes it from any derived or cached voice. It also distinguishes itself from the related patch_brand_voice write path, though that tool is not in the visible sibling list, so cross-tool routing is only partially served.

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?

Explicitly states the targeting rule: pass domain or site_id for a specific site, omit to fall back to the auth default. It also gives an important operational constraint — reuse the same domain/site_id as patch_brand_voice. It stops short of naming a when-not case or an alternate read tool for other scopes.

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