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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety bar is met. The description adds genuine context beyond that: it returns list prices only, it never mutates a selection, and on failure it returns null with a reason rather than erroring — all useful for an agent's planning.

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?

Two dense sentences that lead with the return value and then the input format; nothing is padding. The telegraphic style ('workload: metric=value pairs...') is efficient though slightly clipped.

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?

With no output schema, the description carries the return-value burden and does so: monthly cost, arithmetic string, or null with a reason. Combined with a fully described two-parameter schema, an agent has enough to call it correctly; only explicit sibling routing is missing.

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 100%, so the baseline is 3. The description goes further by defining the workload grammar beyond the schema's examples — 'metric=value pairs or a bare number in the job's primary metric' — which tells the agent a shorthand form the schema does not document.

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 computed resource: monthly cost per candidate from plan limits (base + included + overage), including the arithmetic string or a null with reason. It is clearly distinguishable from listing tools like quote/bundle, though it only gestures at the decision siblings with 'never changes a pick' rather than naming them.

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?

'List prices only; never changes a pick' implies this is an informational estimate rather than a decision step, and 'or null with a reason' signals the failure path. But no alternative sibling (e.g. quote, compare, decide) is named with a condition that selects it, so the when-to-use guidance remains implied.

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