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

Annotations already cover read-only and idempotent semantics, yet the description still adds substantial context: page size 25 with nextCursor pagination, exclusion of revoked/expired/erased/unavailable connections, the caveat that external orders are site attestations not verified payments, and the reassurance that no visitor consent or sending action is exposed. This is rich disclosure well beyond the annotations.

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 scoping and pagination facts are front-loaded and most sentences carry distinct information. It is dense and slightly run-on with several stacked caveats, but there is little outright 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 does describe return content for the 'purchases' action (order amounts, original time, refunds, available email evidence). It is less explicit about what the 'report' action returns and about the payload field semantics, leaving minor gaps for a nested-object, 50%-coverage tool.

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 only 50% and the payload is a free-form nested object, so the description meaningfully compensates by mapping the 'report' action to campaignId/personId and the 'purchases' action to connectionId plus cursor. It adds semantics the generic payload description lacks, though some payload fields (expectedRevision, reviewHash) remain unexplained.

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 states a specific verb (inspect/read) and resource (consented website-reported activity) and distinguishes the two actions internally: 'report' for campaign/person activity and 'purchases' for per-order evidence. It does not explicitly contrast itself with the sibling inspect_email_websites (plural), which an agent might confuse it with, so it stops 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?

It names the account scope ('u_ account only') and the identifiers to supply (campaignId or personId), and points to the workflow guide resource 'socialloop://guides/email-campaigns'. However it never explicitly states when to prefer this over inspect_email_websites or the report-vs-purchases tradeoff beyond the action enum.

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