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

Annotations already cover the read-only, non-destructive, closed-world profile, and the description adds behavior the annotations cannot: each call renders a visible card to the user, so repeated calls are costly, and pageAccess/reachedContent encode whether the check hit a challenge, login or error page. That interpretive rule ("report that, not a change in content") materially changes how the agent uses the result.

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?

Purpose is front-loaded in the first clause, then evidence contents, then interpretation rules, then call-frequency and linking guidance — a sensible ordering with no filler sentences. The opening enumeration of returned artifacts is long, which slightly slows scanning, but each item is informative rather than redundant.

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?

There is no output schema, so the description carries the burden of describing return values, and it does so thoroughly (screenshots, diff, AI summary, extracted current/previous values, HTML copy, pageAccess/reachedContent). For a two-required-param read tool with no output schema, an agent has everything needed to call it once and report it correctly.

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% and both parameters (uuid from list_monitors, checkId from get_check_history) are already documented with their sources in the schema. The description reinforces "by id" and "one specific check" but adds no syntax, format, or constraint beyond what the schema states. Baseline 3 is appropriate when the schema does the work.

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 and resource ("Get the full detail of one specific check by id") and immediately enumerates what the detail contains: screenshots with comparison slider, highlighted difference, AI summary, extracted values, and retained HTML. It also implicitly separates itself from get_check_history (which supplies the id) and get_latest_result (which already shows a check), so an agent can distinguish it from siblings without opening a schema.

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?

Explicit when/when-not guidance: "call it once per check, and not for a check another result already shows (get_latest_result does)", plus a linking rule (use checkUrl, never raw screenshot/diff/HTML URLs). It also tells the agent how to interpret a null-content case rather than misreporting it as a change. Rarely is routing this explicit.

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