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

Annotations already declare readOnly=false, idempotent=true and destructive=false, so the mutation profile is partially covered. The description adds nothing about what dismissing permanently suppresses, whether answering submits a response to a backend, or whether repeated calls change state — the very behavior an agent needs for a UI-state mutation.

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 single sentence is front-loaded and free of padding, but it is concise by omission rather than by discipline. Brevity here costs the agent the only channel it has to learn the patch format.

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?

A mutation tool taking a free-form required object payload with no output schema is the hardest case, and the description supplies none of the missing structure. An agent can guess the operation but cannot construct a correct call from the definition alone.

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 50%, but the documented half is only organizationId ('Approved workspace id only.'). The required 'patch' parameter is an unconstrained object with additionalProperties=true and no description, and the description gives no hint about its shape, allowed keys, or how dismiss differs from answer.

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?

Names a specific pair of actions (dismiss, answer) against a specific resource (referral prompts), which is more informative than the title alone. It is not differentiated from the sibling get_referral, which reads the referral but is never mentioned here.

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?

There is no statement of when to call this versus get_referral or the other referral/billing siblings, and no prerequisites such as an active referral prompt existing. The only guidance is the implied condition embedded in 'Dismiss or answer'.

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