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

Annotations only establish that this is a non-read-only, non-idempotent write; the description goes far beyond that with rate limits (5 extractions/hour, one monthly plan slot), async execution with expected duration, the polling contract via get_profile, and the result field samples_used for user confirmation. It also warns the agent to tell the user which pieces are being sent before calling.

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?

Purpose is front-loaded and every paragraph carries operational content, but the anti-AI-text rule is restated several times ('never AI-generated text', 'never your memory notes or summaries', 'never text you or another AI wrote or rewrote'), which adds length without new 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 mutating, asynchronous tool with no output schema, the description supplies everything needed: input validity rules, sample-count and length thresholds, rate/slot limits, escape hatch via get_billing, and the polling path to completion. Nothing an agent needs to invoke and follow up correctly is missing.

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, but the description adds real constraints not present in the schema: 1-20 samples, each under 5,000 words, 50+ words minimum to count, and 3+ samples totalling 3,000+ words for a confident profile. It does not enrich the name, shared or english_variant parameters, which the schema already documents well.

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 verb and resource ('Create a new voice profile from writing samples') and states the downstream effect ('start the stylometric extraction (45 measured attributes)'). An agent can distinguish this from get_profile, list_profiles and create_company without opening any schema.

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 explicitly states when to use it and what constitutes valid input, including which sources are acceptable ('writing you already hold for the user') and which are not ('never your memory notes or summaries', 'never text you or another AI wrote'). It also routes the agent to siblings at the right moments: get_profile for polling status and get_billing when refused for slots.

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