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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for the extra interaction contract it discloses: 'Show more keeps counting', a pick returning as a user message with (id, url), and the typed-number resolution path against the card or list_images. The trailing 'Free.' hints at a zero-cost call, which is useful but too terse to be certain.

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-loaded with the card shape first and the WHEN clause second, so an agent reads the essential facts in order. The telegraphic, backticked style wastes no words, though phrases like 'Free.' and 'else confirm row n' are compressed enough to risk misreading.

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 parameters, no output schema, and annotations handling the safety profile, the description covers the load-bearing gaps: what the card renders, how a selection comes back, and what to do when no card is available. Only the exact post-pick handoff (does a further tool call follow?) is left implicit.

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 tool takes zero parameters, so the baseline of 4 applies; the schema cannot be improved upon and the description correctly adds no parameter noise.

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 opening clause 'Card: their generated images, numbered, newest first' names the concrete output (an interactive card/picker) and its ordering, which is more specific than a bare verb+resource. It implicitly distinguishes itself from list_images by naming the latter as the no-card fallback, though the agent must infer this is a UI-rendering tool rather than a data fetcher.

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?

'WHEN: they choose one of their images' plus 'No card (terminal): `list_images`' gives both a trigger condition and a named alternative for the fallback case. It also sets a scoping exclusion with 'say one line and stop; never draw them', though the boundary versus show_generation is only implied.

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