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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open world), and the description adds genuinely new behavior: it does not re-search and does not spend credits, and its side effect (card vs. no card) determines what the user has already seen. This is substantive context beyond the structured fields.

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?

Front-loads the action, then sequencing, then the card/no-card branching. Every sentence carries a distinct instruction (when to call, what it avoids, how to respond per host) with no redundancy.

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 one-parameter, read-only display tool with no output schema, the description covers invocation timing, cost behavior, the empty-result case, and the two host response modes. Nothing an agent needs in order to call 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 100% and the schema already defines resultId, so baseline is 3. The description adds sequencing semantics the schema omits by specifying the id comes from the data call that answered the question, clarifying the ordering constraint.

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 and resource ('Show a prior Sightglass result... as an inline card') and immediately distinguishes it from the sibling data/search calls by noting it 'returns the stored result without searching again.' An agent can tell exactly what it does and that it is not a search tool.

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?

Explicit routing: call once, after the data call that answered the question, with that call's resultId; skip for empty results. It also branches on host capability (card drawn vs. no card), removing all inference about when and how to use it.

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