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

Annotations already flag destructiveHint=true and non-idempotence, and the description adds genuinely non-obvious operational behavior on top: a page whose masks or address change gets a new baseline that must be approved, and a hard cap of 40 screenshots per run (pages × devices × browsers). These are side effects an agent could not infer from the schema or annotations.

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 core action is front-loaded before the long enumeration, and each parenthetical (masks purpose, screenshot cap, baseline behavior) earns its place. It is dense and runs long as a single paragraph, which slightly hurts scannability, but there is little waste.

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 destructive 9-parameter mutation with no output schema, the description covers the important ground: side effects (baseline reset), limits (40 screenshots, 10 custom pages), and where to get keys. It stops short of stating permission/auth requirements or what the response returns, leaving a small gap.

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%, so the schema already carries the parameter burden and baseline is 3. The description still adds value by defining masks ('CSS selectors painted over before comparing, for clocks, carousels, ads'), noting the up-to-10 custom-page limit, and restating the threshold unit and defaults, pushing it slightly above 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?

Opens with a specific verb+resource ('Edit the visual regression monitor') and then enumerates exactly what can be edited: pages, masks, devices, browsers, capture mode, threshold, AI review. This clearly separates it from siblings like get_check, list_checks, and update_check, which cover reading and other monitor types.

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 routes the agent to a sibling for prerequisite data ('get_check lists the current pages and their keys'), which is real usage guidance for the update path. It does not, however, state when to prefer this tool over e.g. update_check_settings or add_checks, so the routing is helpful but not exhaustive.

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