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

Annotations declare readOnlyHint=false and destructiveHint=true, i.e. a write operation with destructive potential. The description asserts the opposite with 'without mutation', which tells an agent the call changes nothing. Beyond that conflict, it discloses nothing about what a dismissal does to the decision's state, whether it is reversible, or permission requirements.

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 front-loaded eight-word sentence with no padding or redundancy. It is efficient, though arguably over-terse for a state-changing tool, so it is not maximally sized for the job.

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-read-only tool with no output schema and 0% parameter documentation, the description omits the essentials: what state the decision ends in, whether dismissal is reversible, side effects on the underlying campaign, and how to obtain the required decision_ref. It is not adequate for correct, confident invocation.

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% across two parameters, so the description carries the full burden. It only loosely implies that decision_ref points at a recommendation; it says nothing about the ttdecision_... identifier format or the mctx_v1_... connection_context token, both of which the agent must infer solely from regex patterns.

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 ('Dismiss one open tenant-owned recommendation') with built-in scope constraints ('one', 'open', 'tenant-owned') that make the action identifiable. The only slight weakness is terminology drift: the title/name say 'decision' while the body says 'recommendation', and no sibling is named to differentiate it from the optimization_list_decisions / optimization_prepare_action family.

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 qualifiers 'one open tenant-owned' imply a precondition (only open decisions you own can be dismissed) but it never says where to obtain a valid decision_ref or whether listing tools should be used first. There is no explicit when-not or alternative-tool guidance, so usage is only implied.

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