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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered; the description usefully adds the privacy guarantee ('No logging of addresses') and the dedupe default. However, the response sketch lists verification-style fields (status deliverable|risky|undeliverable, reason, score 0-100, checks run) that read like verify_emails output and are not obviously what an extraction call returns, which risks misleading the agent.

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?

Purpose and scope are front-loaded in the first clause, and the remaining sentences are short, high-density fragments rather than prose padding. Every element (free, pair-with, privacy) carries information.

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?

An output schema exists, so enumerating result/status/score/data_confidence/warnings/disclaimer duplicates structured data and consumes most of the description — and the enumerations look copied from the verification tools, so the agent may expect fields this tool does not return. Core extraction behavior, dedupe, and privacy are covered, leaving the response claim as the gap.

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?

The schema documents 'text' but leaves 'dedupe' with an empty description; the phrase 'deduped by default' fills that gap and tells the agent what the flag controls. Neither param needs format syntax beyond 'any text/HTML'.

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 specific verb and resource ('Find every address in a block of text or HTML') plus a scope detail (deduped by default). This is clearly distinguishable from verify_email/verify_emails, which check addresses rather than extract them.

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?

'Pair with verify_emails' gives an explicit downstream workflow, and 'Free.' signals cost constraints. It does not state when NOT to use it or how it differs from domain_check, but the extraction-vs-verification split is inferable from the first sentence.

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