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

The description adds real context beyond the annotations: answers accumulate into a voice profile with visible progress, and the profile builds from interview answers and drafts. But it never addresses the odd annotation set (readOnlyHint=true alongside destructiveHint=true), so an agent has no way to reconcile 'read-only probe' with a declared destructive operation.

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?

The opening and the brief_id sentence earn their place, but the middle clause is tangled ('Answers accumulate into the author's voice (traits: contractions, I/we, you, dashes, formality, sentence length, directness, number-or-story-first) with visible progress; the measured profile builds itself from their interview answers and drafts meanwhile'). The trait list adds bulk without changing how the agent calls the tool.

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 carries the return-format burden and does so reasonably: A/B pairs, one per line, no explanation, 1–4 count. It omits what happens if the probe cannot be generated, but for a prompt-generating tool the essentials are present.

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 baseline is 3, and the description genuinely extends it: brief_id is explained as sourcing the topic and the author's own facts, and 'one or two per brief' maps the n range to intended usage. site_id is left unelaborated, but the schema label covers it.

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?

States a concrete verb+resource: it returns 'two short sentence pairs about the author's own topic, each written two ways' for an A/B preference choice. That is a distinct output shape from siblings like get_voice_profile, create_voice_profile, declare_voice, and voice_probe_answer, though it never names a sibling to route against.

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?

Gives concrete operating instructions: 'Ask one or two per brief, as A / B, one line each, no explanation,' plus 'Pass brief_id so the pairs use their topic.' It stops short of explicit when-not guidance or naming the sibling that records the answer (voice_probe_answer).

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