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

The annotations include idempotentHint=false, but the description directly says 'Idempotent on already-acked → not found.' This directly contradicts the idempotentHint annotation, which is a serious inconsistency. The approval-tier note adds useful context, but the contradiction caps the score at 1.

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?

The description is front-loaded with purpose and usage conditions, and every sentence adds operational value, including the approval-flow note. It is somewhat dense and jargon-heavy, but not padded or redundant enough to lose more than one point.

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 simple one-required-parameter mutation with no output schema, the description covers the triggering condition, approval behavior, and the already-acked case. The idempotency contradiction undermines completeness, and success-return behavior is not described, so it is adequate but not fully complete.

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?

The input schema covers 100% of parameters with clear descriptions (UUID source and companyId membership requirement). The tool description itself adds no parameter-level meaning beyond that, 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 opens with a specific verb and resource: 'Mark a pending attention directive as acked after the host session has taken the instruction.' It also adds a distinguishing scoping condition, 'for the same operator who owns the queue,' which separates acknowledgment from creating, listing, or canceling directives.

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?

It explicitly states when to use the tool: after the host builder has executed or deliberately skipped a polled directive, and only for the same operator who owns the queue. However, it does not name an alternative tool for the opposite case, so it falls just short of a fully explicit when-not/alternatives statement.

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