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

Annotations already flag destructiveHint=true and idempotentHint=true, so the safety bar is lower; the description nonetheless names the concrete casualty ('It replaces the old baseline'), which makes the destruction tangible in domain terms. It stops short of saying whether the associated incident is closed or what the call returns.

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?

Three short sentences: effect first, default behavior second, side effect third. No filler and nothing 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?

For a 4-param mutation with no output schema, the description covers the write effect and default capture selection. Minor gap: the interaction with incidentId (accepting a capture on a visual incident) is undocumented, so an agent can't tell whether that path also resolves the incident.

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%, so the schema already documents all four parameters including examples. The description adds one genuinely new fact — the omitted-screenshotId fallback to the latest capture — but says nothing about incidentId or visualTargetId behavior, so it does not rise above the baseline.

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?

States a specific verb ('make a capture the new baseline') and the downstream effect ('future checks compare against it'), which is far more than the title alone. It doesn't name sibling tools like vs_visual_capture_now or vs_visual_get, but the action is unambiguous.

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?

Gives one concrete usage rule — 'With no screenshotId the latest capture is used' — which tells the agent it can call without a capture file. There is no guidance on when to prefer this over capturing a new baseline (vs_visual_capture_now) or how it relates to resolving an incident.

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