Export complete open-item evidence as CSV

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds genuine value beyond them: formula-like cells are escaped and no amount-loss or balance total is computed, which tells the agent the output is not a reconciled financial total. It does not state response format or pagination metadata, keeping this short of 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?

Two dense sentences with no filler, front-loading the export action and following with row-granularity and escaping behavior. Slightly harmed by the vague qualifier 'free', which costs a word without adding meaning.

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 carries full burden of explaining the return value; it says one row per source item with side, group and issues, which is helpful, but stays silent on the CSV payload shape, pagination signaling, and how a 'preview:' id contrasts behaviorally with a saved report id.

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 schema gives only types, defaults and a pattern without meaning. The description partially compensates by implying pagination ('pages') and the preview-vs-saved id distinction, but never explains limit/offset semantics or the 2000 cap, leaving the agent to read the schema constraints unaided.

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+resource (export CSV of a report) and adds scope detail about one row per source item with side, group and issues. It implicitly separates itself from report_page via the CSV export framing, but never names the sibling alternative explicitly, and the word 'free' is ambiguous in context.

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?

Usage is only implied: 'from a saved report or unsaved preview' hints at when the id is a preview token versus a saved report, but there is no explicit when-to-use, when-not, or reference to report_page/report_get for the non-export path. An agent must infer the routing decision from sibling names alone.

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