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

Annotations already declare readOnlyHint=true, so the safety profile is covered structurally, and the description adds genuine return-content context (measured ranges per feature, declared answers, plain-language constraints, word count on file). Since no output schema exists, this is the only place the response shape is described — but it discloses nothing about behavior such as what happens when no profile or no writing exists, or what 'destructiveHint=true' alongside readOnlyHint=true actually implies.

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?

It is a single front-loaded sentence with no filler, but the nested parenthetical and the trailing clause 'how many words of the author's own writing are on file toward the measured profile' are convoluted and slow to parse for an agent scanning tool lists. It is concise but not structurally clean.

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 one-parameter read tool with no output schema, describing the returned contents is the right instinct and partially fills the gap. It is still incomplete: the operation itself is never stated as a retrieval, and nothing distinguishes it from voice_profile-creating or voice-declaring siblings, leaving an agent with an accurate picture of the payload but an ambiguous picture of the 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?

There is a single parameter (site_id) with 100% schema description coverage, so the schema does the work. The description adds nothing about the identifier — no format, no note that it scopes the returned profile — which is the expected baseline when coverage is this high.

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 the resource (the brand's voice profile) and enumerates its components, but never states the action — it reads as a noun phrase describing what a voice profile contains rather than 'retrieves the voice profile for a site.' It also does not distinguish this read tool from siblings like create_voice_profile, declare_voice, or voice_probe, leaving the agent to infer the read semantics from the name alone.

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?

There is no when-to-use guidance at all: no mention of prerequisites (must a profile exist?), no note on how it relates to declare_voice or create_voice_profile, and no condition for choosing it over get_brand_profile or voice_probe. The agent gets no routing help.

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