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

Annotations already cover the read-only, idempotent, non-destructive profile. The description adds behavioral value by specifying the two invocation modes and the exact data points returned (cards, rule checks, missing cards, cost). This gives the agent a richer understanding of output behavior beyond what annotations state.

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 sentences with no filler. The resource is front-loaded, and the conditional behavior is organized clearly by argument presence. Every word contributes to understanding.

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?

For a read-only tool with optional parameters and no output schema, the description adequately covers invocation modes and return contents. It could elaborate on the list format or error handling, but annotations and the schema fill the remaining essential context.

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?

The schema documents 'source' but leaves deckId without a description. The description compensates by explaining deckId's role and the resulting output. Together, the schema and description fully explain both parameters, and the description adds meaningful semantics for deckId.

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 clearly states the resource (the signed-in user's saved decks) and the two modes: list all decks without arguments, or retrieve a specific deck's cards, rule checks, missing cards, and finish cost with deckId. It is specific enough to distinguish from collection-level tools like my_collection, but it does not explicitly compare against sibling deck tools such as validate_deck.

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?

It gives clear argument-dependent usage: no arguments returns the list, deckId returns deck details. However, it provides no guidance on when to prefer this tool over alternatives like validate_deck or get_meta_deck, so the appropriate context is implied rather than explicit.

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