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

Annotations already declare read-only, idempotent, open-world and non-destructive, and the description adds substantial context beyond that: a hard 50-match cap, a 'saturated' flag that signals truncation, per-call pricing ($0.020), a free sample invocation, and a clear statement that only derived matches are returned. This is exactly the operational detail annotations cannot express.

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?

Front-loaded with the definition of a look-alike, then cost/sample, then return shape. The telegraphic return-field listing earns its space because there is no output schema. No filler sentences.

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?

With no output schema, the description carries the return-shape burden and does so thoroughly (matches array fields, window_totals, variants_searched, saturated, note), plus cost and the derived-only constraint. An agent knows what it will get, what it costs, and when results are truncated.

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?

Schema coverage is 100% and each parameter already carries its own description, so the baseline is 3. The description reinforces the 14-day window and the notion of risk tiers, but adds no syntax, defaults, or interaction rules (e.g., what min_tier defaults to) beyond what the schema states.

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 resource (newly registered look-alike domains of a brand) and then enumerates the exact match classes: typo, look-alike-character spelling (paypa1), same name on another TLD, or brand+lure word. The example 'paypal-login' makes the scope unambiguous and clearly separates it from sibling tools like domain_available or domain_age.

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?

Gives a clear operational context (14-day registration window, derived matches only) and an explicit negative boundary — 'never a raw list of new domains' — which steers the agent away from treating it as a zone dump. It does not name any alternative sibling tool or state exclusions versus them, so it falls short of a true when/when-not routing rule.

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