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

Annotations only cover readOnlyHint/openWorldHint, but the description goes far beyond: it discloses the required role and plan, the window limits ('7 days at most', up to 60 items), sort order (newest first), and the returned fields (at, rel_min, kind, actor, one-line summary) plus an aggregate count by action. This is exactly the behavioral context annotations cannot carry.

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?

Content is information-dense with little outright waste and the core purpose is front-loaded, but it is delivered as a single run-on block stuffed with semicolon-separated lists. The return shape, constraints, and prerequisites would be far more scannable as separate sentences; structure is a real weakness here.

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 complex investigative tool with no output schema, the description covers prerequisites, the input window semantics, output cardinality and fields, and the ancillary aggregate. An agent has everything it needs to call it correctly and interpret the result.

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?

With 100% schema coverage the baseline is 3, but the description adds a genuine constraint not expressible per-field: the combined window is capped at '7 days at most', and it clarifies the moment-resolution chain ('default: the outage start, else now') that spans multiple params. Defaults are largely restated from the schema, which keeps this from a 5.

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 precise verb+resource: 'What changed on a monitor before a moment' with an enumerated set of change categories (audit log, maintenance windows, mutes, prior outages, SSL, domain). This is clearly distinguishable from siblings like list_audit_log (project-wide) and get_outage_timeline, so an agent can tell what this returns without opening the 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?

Provides strong context for when to reach for it (pre-incident investigation, correlated to an outage or monitor) plus an explicit prerequisite: 'needs the owner or admin role and the plan that includes the Audit Log.' However, it never names alternatives (e.g., list_audit_log, find_correlated_outages) or states when NOT to use it, so routing to a sibling is left to inference.

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