Two sites, read the same way

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

Annotations cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds behavior beyond them: the call is free, resolves instantly, asks no model, and — importantly for budgeting — "counts two identity checks." That quota/cost disclosure is the kind of context an agent cannot get from annotations or schema.

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?

One dense sentence, front-loaded with the core framing ("Your site against a competitor's, read the way an AI engine reads them") before the output list. The enumeration is long but every item is a distinct deliverable, so little is wasted; it borders on list-heavy for a single sentence.

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 annotations carrying safety and an output schema present, the description does not need to explain return values — yet it still sketches them, which aids discovery. Combined with the cost/instant/counts-two-checks note, an agent has enough to call this correctly; only the sibling-routing gap keeps it from a 5.

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 description coverage is 100% and both parameters are documented with examples, so the schema already carries param meaning. The description only restates the roles ("your site against a competitor's") without adding format or constraint detail, which is the baseline-3 case 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 gives a concrete verb+resource (compares two sites as an answer engine reads them) and enumerates the outputs: identity score, crawler access, identity files, Organization schema, and lead differences. It is clear about what the tool produces, but never distinguishes itself from overlapping siblings like atlas_compare, analyze_site, or check_identity, so an agent could still hesitate between 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?

Usage is only implied by "Your site against a competitor's" — the agent can infer this is for benchmarking one site against a rival, but there is no explicit when-to-use, when-not, or named alternative (e.g. use check_identity for a single site). The note that it is "free and instant" hints at a low-cost choice but does not frame it as a routing criterion.

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