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

Annotations only say this is a non-read-only, non-destructive, non-idempotent write, which conveys little. The description adds substantive behavior: which verdicts require elevated role permissions, that "expected" suppresses future alerts, and that the write is gated behind confirm: true. What is missing is what happens on success or failure, or whether a verdict can be revised later — non-idempotence is declared in annotations but never explained.

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 tight sentences, front-loaded with purpose and then the operational constraints. The parenthetical definitions do real work; nothing is wasted or repeated from the schema verbatim.

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 non-destructive write with no output schema, the description covers the essentials an agent needs to call it safely: allowed verdicts, role gate, and confirm gate. It is slightly thin on outcome (does the incident state change immediately, what is returned) and omits the multi-project requirement, which lives only in 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?

With 60% schema coverage, the description meaningfully annotates two parameters: the verdict enum values each get a gloss, and confirm is reinforced with an absolute rule. It says nothing about project (multi-project tokens), note, or incident_id beyond what the schema already carries, so the remaining coverage gap is not closed.

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 ("Teach Relia about an incident") and, unusually, defines each of the five verdict values in plain language ("correct (real), wrong (false alarm), expected (by design, stop raising it)..."), which tells an agent exactly what the tool changes. It never distinguishes itself from close siblings like relia_ack or relia_mark_fixed, so an agent still has to infer which tool applies in a given case.

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 two real preconditions: role requirements ("expected / mute / bug need an owner or admin") and a mandatory confirmation gate ("Nothing happens without confirm: true"). However, there is no guidance on when to choose this over relia_ack or relia_mark_fixed, and no statement of when-not to raise a verdict, so the selection context is only implied.

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