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

Annotations are minimal (readOnlyHint=false, openWorldHint=false, destructiveHint=false), and the description adds substantial context beyond them: the two-result structure with no blending, a 1-credit cost for Stance, that Stance only runs when the claim bank has items and the text asserts something, that Style is free, and that text is 'checked once.' This also explains the non-read-only annotation (credit consumption). Rich behavioral disclosure.

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 core distinction (two separate results, no blended score) is front-loaded, and each subsequent clause earns its place by defining Style, Stance, cost, and gating conditions. It is dense and somewhat run-on, but there is little waste.

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?

There is no output schema, so the description carries the burden of describing returns — and it does: Style as 'N of M checks' with named checks and an example line, Stance as 'On voice / Check one line / Off voice' with flagged lines and matched claims. For a single-parameter tool this is complete enough to call and interpret 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?

There is a single parameter with 100% schema description coverage, so the schema already documents the 'content' field and its 8000-character scoring limit. The description restates 'the exact text to score' but adds no syntax, formatting, or truncation behavior beyond what the schema states. Baseline 3 applies when the schema does the heavy lifting.

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+resource — checking a piece of text against the user's voice — and immediately disambiguates the output into two distinct results (Style vs Stance). It also explicitly states 'There is no blended voice score,' which separates it from any generic improve/score sibling like improve_post. An agent can identify the tool's function without opening the 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 gives clear triggering conditions: 'Use when the user asks whether a draft sounds like them, is on voice, or is something they would write, including a draft written for them in this conversation.' It also scopes Stance to claim-bank items and text that states something checkable. It does not explicitly name a sibling alternative (e.g., improve_post) to route away from, so it stops short of full when/when-not guidance.

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