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

Annotations already cover read-only false, idempotent true, destructive false, open world true. The description adds valuable behavioral context: the user completes a human check in their browser, a short-lived access code is emailed, and the tool never submits a lead. This goes beyond annotation basics, though it omits details like rate limits or failure outcomes.

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 description is three sentences, front-loaded with the core action, then delivers essential workflow instructions with no waste. Each sentence earns its place.

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 description covers the full workflow, return value (humanCheckUrl), and user interaction steps adequately for an agent to execute correctly. It misses explicit parameter meanings, especially idempotencyKey, but overall the flow is well-specified.

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, the description must compensate for all three parameters. It implicitly explains email (where the code is sent) and confirmed (user agreement), but idempotencyKey is never mentioned or clarified. The purpose of that parameter remains opaque, leaving a significant gap.

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 states a specific action ('start authorization') on a specific resource ('their own inquiry'), with a clear precondition ('After the user agrees'). It explicitly distinguishes itself from sibling tools with 'Never submits a lead,' so an agent can differentiate it from prepare_inquiry and submit_inquiry.

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 provides clear when-to-use context ('After the user agrees') and strong exclusions ('Never submits a lead,' 'Do not open the link yourself'). It also instructs the agent to ask the user to paste the code. However, it does not explicitly name alternative tools (e.g., 'use submit_inquiry instead'), so it falls short of perfect guidance.

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