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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real behavioral value on top: result ordering (newest first) and the exact composition of the feed, including that incidents appear only when they 'began' in the window. It stops short of disclosing result caps or how large windows are truncated.

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?

A single dense sentence that front-loads the core answer ('What changed lately, newest first') before the enumeration. The nested colons and em dash make it slightly harder to parse than necessary, but no sentence is wasted.

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 only two fully documented optional parameters and rich annotations, the main remaining burden is describing the return content, which the description does by enumerating the three change classes. There is no output schema, so a brief note on item shape or result limits would have closed the last gap.

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%, and both parameters (hours with its default 48 and project scoping) are fully documented in the schema itself. The description adds no further semantics about the time window or project scoping, 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?

States a specific resource (a merged change feed) and enumerates its three constituent classes: deploys Relia saw, changes reported to Relia, and incidents that began. The phrase 'newest first' plus the incident framing distinguishes it from relia_list_incidents and relia_report_change without the agent needing to open any 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?

Gives a concrete triggering question — 'did my deploy break anything?' — which is a strong, recognizable use case. It does not, however, name an alternative or state when to prefer relia_list_incidents or relia_get_incident instead, so there is no exclusion guidance.

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