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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds decision semantics ('REFUSED means do not offer it', OFFER_* refuse things the plan lacks), which is useful, but since an output schema exists the return shape is already handled and no auth/rate-limit context is added.

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?

Four tight sentences, front-loaded with the core decision, with no padding. The only cost is that 'REFUSED' is referenced before its meaning or source is established, making the opening slightly opaque.

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 tool with 5 parameters, three enums, conditional input requirements, and 0% schema coverage, the description is too thin. It covers the action-level semantics but omits the parameter-to-action mapping and any prerequisite context an agent needs to invoke it 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 description coverage is 0% across 5 parameters, so the description must compensate and largely does not. It never mentions catalogId, planId, or the conditional requirements (channel for OFFER_CHANNEL, staffingKind for OFFER_STAFFING), leaving the agent to infer which inputs are needed for which action.

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 ('Decide') and resource (plan coverage of reply window, channel, staffing promise), which maps onto the three action enum values. It is distinguishable from the list_* siblings, though the framing is terse and relies on jargon (REFUSED) that is not defined.

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?

Explicitly routes the agent to a sibling: 'Permission to state wording still requires evaluate_support_promise for the exact text,' and gives an action rule ('REFUSED means do not offer it'). It does not say when to prefer this over list_plan_channels or how the three actions map to required inputs, so it stops short of a 5.

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