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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds meaningful behavioral context: images are bounded previews and only up to four can be viewed. This goes beyond the annotations without contradicting them.

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?

The description is three short sentences with no filler. The most important purpose statement is front-loaded, followed by parameter provenance and a clear usage condition. Every sentence earns its place.

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 simple two-parameter tool with rich annotations and an output schema, the description is largely complete: it covers what the tool does, how to obtain refs, the preview limitation, and when it is appropriate to call. The only minor gap is not describing behavior for stale or invalid refs, but that is a secondary edge case.

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%, so the description must explain the parameters, and it does meaningfully. 'Use refs returned by image-ranked search or fetch' tells the agent where refs come from and that they are opaque image selectors, not arbitrary URLs. The phrase 'from a bookmark' ties the id parameter to the bookmark context, though the exact format of refs is not spelled out.

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 begins with a specific verb and resource: 'View up to four selected stored images from a bookmark.' It also indirectly distinguishes itself from siblings like search and fetch by focusing on stored images and previews. An agent can tell this is a read-only image viewer rather than a general fetch or 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?

The description gives clear usage context: use refs returned by image-ranked search or fetch, and call only when visual inspection is useful. It provides an explicit condition for when not to call ('only when visual inspection is useful'), but it does not name a concrete alternative tool for non-visual use cases.

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