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

Annotations already declare readOnly, idempotent, and non-destructive, so the bar is lower; the description adds real value beyond them by disclosing that results are "not metered," that paging requires reading next_cursor "while more remain," and that each row carries member evidence plus each chart's latest judgment. It does not mention any auth/permission prerequisite or how retired events behave beyond the schema's default, keeping it from a 5.

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?

Three sentences, front-loaded with purpose then filter surface then return shape; no filler. The middle sentence is dense and packs several concepts (five filter axes plus paging) into one clause, which is efficient but slightly crowded.

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?

Given an output schema (so return-shape detail is optional) and rich annotations, the description still covers filters, pagination, and per-row content, leaving little ambiguity about how to call it. Minor gaps remain around what happens when no events match or whether pending evidence is excluded, but nothing essential to correct invocation is missing.

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%, so the baseline is 3, and the description largely restates what the schema already documents (kinds, filters, date window semantics, cursor paging). The one addition beyond the schema — the next_cursor read pattern — is also already implied by the cursor property's description, so no genuine lift over structured data.

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 verb and resource ("Lists the events") and immediately qualifies the resource's provenance and subtypes ("derived from admitted evidence — movements, claims, and itemizations"). This is enough to distinguish it from siblings like list_review_items, list_chart_accounts, or list_workspace_account_activity without opening a schema.

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?

Enumerates exactly what can be selected on (kind, endpoint account, owning party, reviewing chart, inclusive date window) plus pagination behavior, which gives an agent concrete selection criteria. It stops short of naming an alternative or a when-not case (e.g., use review items instead when you want unreviewed judgments), so it is not a full 5.

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