What changed before an incident

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, but the description adds substantive semantics beyond them: network uses interval matching so a request failing inside the window counts even if it started earlier, and baseline directions are reported as unknown rather than fabricated when observation predates the window. These edge-case disclosures are exactly the kind of 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?

It is one dense, front-loaded block that leads with what is returned before the mechanics. Every clause contributes information (dimensions, directions, anchoring, interval matching, baseline honesty) with no filler, though the nested parentheticals make it heavier than it needs to be.

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 no output schema, the burden of describing returns falls on the description, and it does so thoroughly: dimensions, direction vocabulary, and citable evidence are all covered, as are anchoring fallbacks and the baseline edge case. Safety behavior is covered by annotations, so the only mild shortfall is the absence of any usage routing against siblings.

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 are already well documented, including the eventId default and windowMs bounds. The description largely restates the anchoring default and adds no format or constraint detail beyond the schema, so the baseline 3 applies.

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 names a specific analytical operation — measuring the incident window against an equal preceding baseline, per dimension, with directions and citable evidence. That baseline-comparison framing distinguishes it from plain sibling readers like get_timeline or get_exceptions, and the listed dimensions make the resource concrete.

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?

Usage is only implied: it is for reconstructing what preceded a failure, and the anchoring rules (eventId, else most recent exception, else now) are stated. There is no explicit when-to-use/when-not or routing to alternatives such as diagnose_performance or explain_diagnosis, which is a real gap given how many overlapping diagnostic siblings exist.

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