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

Adds real context beyond the annotations: the capture is compared to the baseline, occurs outside the schedule, can be rejected with two named error codes, and is rate-limited per workspace. It leaves one behavioral gap — since idempotentHint=false, the agent would benefit from knowing whether repeated calls overwrite or accumulate captures/baseline state.

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 tight sentences, front-loaded with the action and its comparison effect, then the gating conditions and error codes. The closing note about per-workspace capture limits is slightly clipped and underspecified, but nothing is wasted.

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 3-param mutation with no output schema, the agent gets purpose, preconditions, error behavior, and throttling context. What's missing is the observable outcome — whether the call returns the comparison result/diff or just an acknowledgment — which matters since there is no output schema to fall back on.

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 100%, with id, fullPage (including the default fallback to the monitor setting), and visualTargetId all documented in the schema. The description adds no parameter-level detail, so the baseline 3 applies.

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+resource+effect: take a fresh screenshot of a monitor's page now and compare it against the baseline. It is distinguishable from the scheduled capture path ('in addition to the schedule'), though it never disambiguates against the sibling vs_subpages_capture_now, which reads similarly.

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 explicit preconditions and outcomes: only for monitors with visual checks enabled and within the plan's visual monitor limit, otherwise refused with VISUAL_DISABLED or LIMIT_EXCEEDED. It does not name an alternative tool to use when refused, nor clarify monitor-page vs subpage capture, so it stops short of a 5.

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