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

Annotations declare readOnlyHint=false and non-idempotent, which would otherwise be puzzling for what looks like a read; the description resolves this by stating 'Uses one read and saves the result in the user's Puley history,' explaining the write side effect and the cost of each call. It also discloses the external open-world sources (public registry, Trustpilot) and sets the interpretive frame that the output is signaling rather than adjudication.

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 content is front-loaded: the purpose and full list of returned facts lead, followed by the verdict caveat, the parameter format, and the side-effect note. The parenthetical source attributions are dense but each earns its place by telling the agent where the facts come from.

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 must describe returns, and it lists the Trustpilot fields and registry fact in enough detail for an agent to plan around. It does not describe behavior on domains with no Trustpilot profile or an unregistered site, nor the response shape, which leaves a modest gap for a single-input tool of this kind.

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 0%, so the description carries the full burden, and it does: 'website: a domain such as example.com, or a link' tells the agent both accepted input forms and gives a concrete format example. That is meaningfully more than the bare 'Website' string property in the schema.

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 names a concrete deliverable and enumerates its two data sources precisely: domain first-registration date from the public registry and a Trustpilot record (TrustScore, review count, 1-star share, summary, alerts, latest reviews). An agent knows exactly what comes back. It does not explicitly route away from overlapping siblings such as is_it_real, read_reviews, or company_brief, so it falls short of the top of the scale.

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?

'Facts to judge whether an online shop or company is trustworthy before buying' gives a clear situational trigger and set expectations with 'gives signals, not a verdict.' There is no explicit when-not guidance and no named alternative for cases where the agent wants reviews-only or company-level data, which keeps it below a 5.

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