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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds real value beyond that by disclosing the divergent return shapes — inline text for tsv versus a one-click download link for pdf — which is exactly what an agent needs to chain a follow-up call.

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 sentences, zero waste, with the deterministic set of outcomes front-loaded right after the action. The format-behavior mapping is stated once and completely.

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 the burden of describing return values and does so for both branches. Minor gaps remain — nothing on whether the pdf link expires, whether export is synchronous, or behavior on a missing set id — but nothing an agent must know to invoke it correctly 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 50%: setId is documented in the schema, but the format enum has no per-value description. The description compensates by explaining what each enum value produces, which is the more consequential parameter here.

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 (export) and resource (flashcard set) and immediately names the two output modes, so the tool is distinguishable from get_flashcard_set and export_quiz by action rather than by an explicit sibling callout. Clear but no explicit sibling differentiation.

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 by the format descriptions: an agent can infer 'use tsv for Anki import, pdf for human download,' but the description never says when to pick this over get_flashcard_set or how to handle a failed export. No exclusions or alternatives are named.

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