exceptions_report

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

readOnlyHint=true already declares the safety profile, so the '[READ]' prefix is largely redundant. The description does add useful content scoping — it says the report covers denials, errors and budget-exceeded ops — but says nothing about volume limits, pagination, or how results are aggregated.

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?

Front-loaded with the read tag and the resource, followed by a one-line rationale and a compact args block. The 'not rubber-stamp' clause is motivational framing that is slightly ornamental but still carries interpretive value.

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?

There is no output schema and no annotations beyond readOnlyHint, so the description must carry the load. It identifies the report's contents but leaves open what happens when since/until are omitted (both default null) and what the returned evidence looks like.

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 0% and the schema only supplies an 'anyOf' string/null type for each field. The description compensates by naming both parameters and giving their format ('ISO timestamps') and role ('bounding the period'), which is the key information the schema lacks.

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 resource — denied, error and budget-exceeded operations — with the analytical angle (enforcement + anomaly evidence). An agent can tell what this report contains, though it isn't explicitly differentiated from siblings like approval_report or query_audit_events.

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 explains why the report matters ('denials prove the governance controls actually block') but never states when to reach for it versus the many sibling reporting tools (coverage_summary, approval_report, query_audit_events). No exclusions, prerequisites, or alternatives are offered.

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