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

Annotations only mark this as a non-destructive, non-open-world write; the description adds substantive context beyond them: feedback is private, screened before storage, does not authorize other actions, and should not be retried when the outcome is uncertain (consistent with idempotentHint=false). It also carries concrete data-handling prohibitions (no credentials, personal/customer records, full conversations, or raw payloads).

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 purpose, then requirement, then safety constraints, and nearly every sentence is a distinct operational rule. It is dense but justified for a tool with privacy and data-handling hazards; only the placeholder instruction feels slightly compressed rather than placed with the other data rules.

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 four-parameter tool with no output schema and no annotation detail, the description covers purpose, required input, privacy constraints, and retry policy well. The residual gap is what a successful submission returns and how `context` should be populated, which the description leaves implicit.

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%, so the description must carry parameter meaning, and it only identifies which parameter is required versus optional (message vs category/toolName/context). It never explains what belongs in `context` versus `message`, or what format `toolName` expects, so an agent still has to guess at the two least obvious fields.

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 (send private feedback) plus the recipient (the Skai team) and enumerates the accepted content types. Nothing about it can be confused with the sibling tools, which are all Norwegian company-data lookups.

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 explicit when-to-use guidance ('Report once per distinct observation and continue your task') and explicit when-not guidance ('Do not report failures of this feedback tool or automatically retry an uncertain submission'). It also states the minimum viable call ('Only message is required'), leaving no routing ambiguity.

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