Read complete open-item evidence pages

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one useful behavioral fact: unsaved previews last 30 minutes. However, it does not explain what a preview is, which sections produce previews, or how pagination interacts with preview expiry, and the phrase 'last two checks' is ambiguous.

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 description is short and front-loads the read operation, but the second sentence is cryptic and the phrase 'free pages' is vague. Two sentences do not feel padded, yet they leave the reader with unresolved ambiguity rather than crisp operational guidance.

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?

For a paginated read tool with five parameters, zero schema descriptions, and no output schema, the description is insufficiently complete. It does not explain how to page through results, how section values map to the described content types, the role of group_id, or what preview identifiers look like. The 30-minute TTL is a useful fragment but does not compensate for the missing operational context.

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% for five parameters, so the description must compensate but mostly does not. It hints at section categories but never names the enum values or explains that group_id is required when section is group_members. The id format (report vs preview), limit maximum, and offset semantics are undocumented in both schema and description.

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 read operation over pages of source lists, group summaries, or group members, which loosely maps to the section enum. However, the phrasing 'source list' and 'one group’s source members' does not align with the actual section values (statement_records, ledger_records, groups, group_members), leaving the agent to infer the mapping. It is distinguishable from report_list and report_get as a paginated section reader, but only weakly.

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?

There is no guidance on when to use report_page versus report_get, report_list, or report_export_csv. The mention of 'the last two checks in this process' is cryptic and does not clarify the selection criteria. No prerequisites, pagination continuation guidance, or exclusions are provided.

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