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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile needs no restating. The description adds the useful temporal framing ('prior audits', 'the trend'), but says nothing about ordering, retention, or whether history is empty for new sites. Output schema exists, so return shape is not its burden.

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?

Two short sentences, and the highest-value content (the call trigger) is front-loaded. Nothing is padded or repeated from the name or title.

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 and full parameter coverage, the description only needs to supply selection guidance and it does. Minor gap: how the default limit of 10 behaves for trend analysis is left entirely to the schema.

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 both parameters (siteId, limit with min/max/default) are already documented in the schema. The description adds no semantics beyond that, which is the expected baseline 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 ('Returns prior audit metrics') plus the analytical purpose ('see the trend'), which separates it from get_audit_report and compare_audits. It stops short of naming the siblings it is not, so differentiation is inferred rather than explicit.

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?

'Call before a large change or when investigating a regression' gives a concrete trigger condition, stronger than implied usage. It never names alternatives such as compare_audits for side-by-side comparison, so the when-not case stays open.

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