getSiteAuditChanges

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds meaningful behavioral nuance: regression is tracked via durable issue identity, not list comparison, and the baseline advances automatically unless overridden. This goes beyond the annotations and gives the agent confidence in how results are computed.

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 three paragraphs but each sentence earns its place: purpose first, then composition, then the regression nuance, then the baseline override. It is well-structured and front-loaded, though slightly longer than strictly necessary.

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 tool with an output schema and rich annotations, the description covers the essential context: what it returns conceptually, the default/comparison behavior, and the underlying accuracy mechanism. The agent has everything needed to invoke it correctly without further investigation.

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% with parameter descriptions for both auditId and baseline. The description adds extra semantic value by explaining the default baseline behavior and referencing source tools (startSiteAudit, listSiteAudits) for auditId. It clarifies usage beyond the schema, which is a bonus.

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 the exact question it answers: 'what changed on this site, and what should I fix first?' It then lists the concrete components (new/fixed/regressed issues, score delta, prioritized groups) and distinguishes itself from sibling tools like getSiteAuditReport by focusing on delta vs. a full report. This is specific and unambiguous.

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 states it applies to completed audits and explains the optional baseline parameter to compare against a specific earlier audit. It does not explicitly name alternatives or when not to use it, but the context is clear enough that an agent can infer its place among siblings.

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