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

Annotations declare a non-read-only, non-idempotent, non-destructive write but say nothing about the commit gate; the description supplies that with 'Nothing happens without confirm: true,' which is exactly the kind of two-phase behavior an agent must know. It stops short of saying what a successful report returns or whether repeated reports dedupe.

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 short sentences, front-loaded with purpose then the hard constraint, with zero filler. The confirm rule is placed last where it is most memorable before invocation.

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 seven-parameter write with no output schema and thin annotations, the definition covers intent and the confirm gate but not the remaining payload fields or what the call returns. Adequate to avoid misuse of confirm, insufficient to fill the fields correctly.

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 only 29% (two of seven parameters documented), so the description must compensate. It maps loosely onto 'kind' by naming deploy/config/flag, but leaves note, service, version and previous_version entirely unexplained — an agent cannot tell what to put in previous_version or how note is used.

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 ('Tell Relia about a deploy, config change or feature flag') plus the effect ('links problems to it and verifies fixes'). The 'it can't see' qualifier implicitly separates it from relia_changes, which presumably surfaces known changes, but that sibling is never named.

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 parenthetical 'e.g. right after deploying a fix' gives one concrete trigger, and 'it can't see' implies a precondition. However, there is no explicit alternative ('use relia_changes to read reported changes') and no guidance on when not to report, so the agent must infer routing.

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