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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description adds genuinely useful behavioral context beyond them: no new check is started, and both results must still be unsaved/available, which is a real operational constraint. It could say more about how long results remain comparable.

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?

Four short, front-loaded sentences; the core action comes first, followed by the source of inputs, the non-side-effect guarantee, and the precondition. No sentence 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?

With an output schema present, return values need not be explained, and the description covers prerequisites, input origin, and the no-new-check behavior. The 'must still be available' constraint could be sharpened (how long, what happens otherwise) to be fully complete.

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 each nested field (jobId, accessToken) is already documented with origin and secrecy guidance. 'Uses the handles from check_website' largely restates what the schema already says, adding little new meaning, 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 and resource ('Compare two completed checks of the same page and device, before and after a change') and immediately distinguishes itself from check_website by clarifying 'No new check is started.' An agent can tell this apart from starting a check or fetching a single check without inspecting schemas.

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 clear context for use (before/after a change, using handles from check_website) and a meaningful precondition ('Both unsaved results must still be available'). It does not explicitly name what to use instead when results are no longer available, so it stops short of 5.

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