What changed since last check

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

Annotations already flag readOnlyHint and destructiveHint, and the description adds meaningful behavioral context: the domain must be tracked, a paid Website Auditor subscription is required, and the return includes specific deltas like score movement and engines gained/lost. It also discloses trial terms and payment requirement, which is useful for setting user expectations. It stops short of discussing rate limits or error behavior, but those are not major omissions for this read-only tool.

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 description is longer than average, but the length is earned: it covers use cases, prerequisites, return contents, and subscription/fallback details. The core purpose is front-loaded in the first sentence, and the additional detail is actionable. It is slightly verbose around the subscription trial explanation, but not distractingly so.

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 read-only, two-parameter tool with no output schema, the description is complete: it states what the tool returns, what preconditions exist (tracked domain, subscription), and what fallback to use when the user does not have the paid plan. There are no significant gaps that would prevent an agent from invoking 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 description coverage is 100%, so the schema already documents 'domain' and 'since' (including the 'last_check' option). The description indirectly clarifies 'since' by saying 'since it was last checked' and referencing week/month, but it does not add meaningful parameter-level details beyond the schema. This aligns with the baseline 3 for fully covered schemas.

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?

The description opens with a specific, actionable statement: 'Report what changed in a website's AI visibility and audit since it was last checked.' It then lists concrete user phrasings ('did anything change,' 'what's different this week/month'), which makes the tool's purpose unmistakable and distinguishes it from sibling tools like get_ai_visibility or get_sample_audit.

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?

The description provides explicit when-to-use guidance through example queries, states the prerequisite that the domain must be tracked and points to track_site, and gives a clear alternative path: call get_sample_audit first if the user lacks a subscription. This is strong routing behavior that helps an agent choose correctly.

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