See the page

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

Annotations only declare readOnlyHint=true, so the description carries most of the behavioral load, and it does add real value: a ~1,500 token cost estimate and the fact that the input must be a snapshot_id from observe or a prior action (a provenance constraint). It does not say what happens with a stale or invalid snapshot_id, nor whether the image is returned inline or as a reference, which is the remaining behavioral gap.

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 sentences, no padding: the output is described first, then the cost and selection criterion. The most decision-relevant fact for an agent (token cost) is placed before the guidance clause rather than buried.

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 must characterize the return value, and it does reasonably well (image with id badges on actionable elements). Combined with the cost note and provenance rule, an agent can call it correctly, but the absence of any failure-mode or freshness caveat for snapshot_id leaves a real hole for a tool whose only input is a handle.

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 0% and the single parameter `snapshot_id` has no schema description, so the description must compensate — and it does, by stating where a valid snapshot_id comes from (observe or an action) and what it produces. It still doesn't describe the expected format of the id itself (opaque string vs. structured handle).

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 the concrete resource: a screenshot rendered from a snapshot_id returned by observe or an action, with every actionable element outlined and tagged with an id badge. That element-overlay detail implicitly separates it from a plain capture tool, but the sibling literally named 'screenshot' is never mentioned, so the agent must infer the boundary rather than being told it.

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 an explicit positive trigger — 'use it when the text listing is not enough (layout, an image, a visual state)' — and a cost-based reason to prefer text output first. It stops short of an explicit when-not/alternative statement (e.g. use `screenshot` when you don't need element ids), leaving that choice to inference.

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