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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description only needs to add context. "Bounded" hints at the recordLimit cap, but it omits the significant non-idempotent behavior (repeat calls spawn duplicate jobs), any auth/rate-limit notes, and lifecycle expectations. Minimal value beyond 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?

A single tight sentence with the verb front-loaded and no filler. It is efficiently written, though its brevity here reflects under-specification rather than disciplined editing.

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?

No output schema exists and no annotations describe returns, yet the description says nothing about what the created job yields, its identifier, status, or how pagination/cursor interacts with recordLimit. For a 5-parameter mutating tool with 0% schema coverage, this is a substantial gap.

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% across 5 parameters, so the description carries the full explanatory burden. It only gestures at bounding via "bounded" and never explains cursor, format, selectionStrategy (balanced vs recent), or the recordLimit maximum of 500. The two enums are left entirely to the schema.

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?

Specific verb+resource ("Create ... export job") that cleanly distinguishes it from the sibling read tools evidence_get_export, evidence_get_export_artifact, and evidence_get_export_manifest. However, it states the job is "JSONL" while the format parameter also accepts parquet, which slightly narrows the tool's actual scope.

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 versus the retrieval siblings, no mention of prerequisites, auth, or what to do after the job is created. The agent must infer the entire create-then-fetch workflow 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.