Load one exact preview for explicit headless review

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds that the preview is model-visible and limited to one candidate, but it does not explain exactSelector resolution, failure behavior, or whether the preview affects the library in any way. 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?

Two short sentences front-load the core purpose and follow immediately with the most important invocation constraint. Every sentence earns its place, with no filler or 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?

The invocation context is well covered, but the tool has an undocumented nested exactSelector object and no output schema. An agent would likely be unsure what keys/values exactSelector requires, what providerId and resultSetId refer to, or exactly what the returned preview contains beyond being 'model-visible'.

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?

With 0% schema description coverage and three required parameters, the description needs to compensate, but it never explains providerId, resultSetId, or how to construct the nested exactSelector object. The phrase 'one exact preview' provides only a weak hint that exactSelector identifies a single candidate.

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 clearly identifies the resource as 'one exact preview' and makes the headless/model-visible scope clear, distinguishing it from general preview or working-revision preview tools. It lacks an explicit action verb in the description itself, though the title and 'Model-visible exact preview' make the action unambiguous.

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?

The description explicitly states when to call ('only after the user selects a candidate, explicitly delegates visual review, or an App updateModelContext handoff selects one candidate') and warns against iterating through all results. It provides clear when/when-not guidance but does not name alternative preview tools, so it stops short of a 5.

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