Read full candidate evidence pages

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), so the description need not repeat that. However, the description adds little beyond a cryptic note about preview ids expiring in 30 minutes. It doesn't explain pagination behavior, what 'free pages' means, or how the 'last two checks' relate to the preview id lifetime. This is insufficient behavioral context for a read tool with no output schema.

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 brief, but the second sentence about preview ids is confusing and lacks structure. It is not front-loaded with the tool's purpose; instead it leads with 'Read free pages' which is ambiguous.

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 no output schema and 0% parameter documentation, the description fails to provide enough information for an agent to correctly use the tool. It does not clarify what sections correspond to which enum values, how id and preview ids work, or what the return data looks like.

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%, and the description does not explain any of the five parameters. The critical 'section' enum values are listed vaguely as 'records, group summaries, record reasons or one group's members', but the mapping to the actual enum values (records, groups, record_summaries, group_members) is unclear, and group_id, limit, offset, and the id format (including preview: prefix) are entirely unaddressed.

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 the resource ('records, group summaries, record reasons or one group's members') but uses a vague verb 'Read' and does not clearly distinguish this tool from siblings like report_get or report_list. It's unclear whether this is a paginated viewer, an export, or something else specific.

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?

No guidance on when to use this tool versus alternatives such as report_list or report_get. The description does not state prerequisites or conditions for invocation, leaving the agent to guess based on the name.

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