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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive). The description nonetheless adds real behavioral context: global scope across all sets, sort order, and the special limit=0 mode that returns counts only. It stops short of explaining pagination or whether counts reflect the limit.

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 compact clauses with zero filler; the queue definition and ordering come first, then the counts and limit=0 behavior. Every phrase carries information an agent needs.

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 does the work of describing returns: due cards, due count, and learned-today count. Adequate for a one-parameter read tool, though it omits card field shape and whether counts are affected by limit.

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 the single limit parameter, so the description must compensate. It explains the limit=0 sentinel, which the schema cannot, but never states that limit caps the number of returned cards or that the maximum is 100. Partial compensation only.

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?

Names a specific verb and resource ('Get the user's spaced-repetition review queue: flashcards due now across all sets') and adds the ordering rule (oldest due first). This is clearly distinct from sibling reads like get_card_states or list_my_flashcards, which do not describe a due queue.

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 implied by the resource: this is for retrieving cards due for review. Nothing is said about when to prefer get_card_states or how this relates to starting a review session, and there are no exclusions or preconditions. The limit=0 tip is a useful usage note but not a routing rule.

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