Check a draft for habits repeated across a voice's past pieces

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

Annotations already declare safe read-only/idempotent behavior, and the description adds valuable context: it lists the two specific repetition patterns, empty-list behavior for insufficient history, local-only history tracking, and a caution not to over-trust results. No contradiction with annotations.

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?

Four sentences, each earning its place: purpose, distinction from audit_text, usage conditions including empty-list behavior, and a trust-mode warning. Information is front-loaded and compact without redundancy.

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?

Even without an output schema, the description fully sets expectations: what the tool detects, when it may return empty, platform differences, and how to interpret its signal. This is sufficient for an agent to invoke it correctly.

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?

Input schema covers all three parameters with clear descriptions: text, styleId, and deprecated id alias. The tool description adds context about trained voices and recent samples but does not substantially enhance parameter-level meaning beyond the schema, so baseline 3 is appropriate.

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 specifies a clear action: comparing drafted text against a trained voice's samples to detect two named types of self-repetition. It explicitly differentiates from audit_text ('not AI-writing tells') and ties to train_style, making its purpose distinct among siblings.

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?

Directs users to use audit_text for AI-writing tells, and states that the tool is only meaningful for voices trained from real samples with at least 3 samples, otherwise returning empty findings. It also notes hosted/remote differences and advises against rewriting solely on this signal, covering when-to-use and exclusions.

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