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

Annotations already cover readOnly, openWorld, idempotent and non-destructive, and the description layers on materially new behavior: a 24-hour cache, the explicit limitation that it cannot see inside accounts (so Google Business Profile or tag ownership is reported as a check, never guessed), and a plain-words statement of what the response contains. That is exactly the kind of beyond-annotations context that prevents misreading results.

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 opening clause front-loads the core purpose, then the sentence chain expands into detail rather than burying the point. It is dense and list-heavy (ten-plus platform names, many tag types), but those enumerations serve to tell the agent which signals are detectable. Slightly overgrown, but nothing is filler.

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 contract itself: per-layer controller, portability rating, plain-words reason, evidence, sources, suggested first step, plus a 0-100 portability score. Combined with the stated accuracy boundary and the cache TTL, an agent has everything needed to call it and interpret the result.

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%, so all three parameters are already documented in the schema, including that profile_urls are classified not fetched and business_name is compared against the public registrant. The description restates the Google Business Profile / profile-links role but adds no format, limit or semantics beyond the schema. Baseline 3 is appropriate.

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 precise verb and scope: mapping who controls each layer of a business's web presence and how portable each layer is, all from public data. It enumerates the layers and data sources (RDAP, DNS, MX/SPF, page fingerprints), so an agent knows exactly what work the tool does. It does not, however, explicitly differentiate itself from siblings check_domain_control or list_fingerprints, so it falls short of a 5.

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 implied rather than stated: an agent can infer this is the broad multi-layer audit, but the description never says when to prefer it over check_domain_control or list_fingerprints. It does add a boundary condition ('from public data only') and clarifies that profile links are classified, not fetched, which nudges toward correct invocation. No explicit when-not or alternative routing.

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