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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the bar is lower. The description adds real behavioral context the annotations cannot: coverage comes from each plan's Benefit Schedule, cost is the published premium for every year from this age, and a second cost figure applies the insurer's filed rate changes. It says nothing about auth needs, rate limits, or result determinism.

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?

Front-loaded with the tool's identity, then the output shape, then the cost methodology, then the one actionable instruction about inputs. Every sentence carries information, though the premium/rate-change sentence is dense and could be tighter.

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 13-parameter tool with 85% schema coverage, full annotations, and an output schema, the description still manages to disclose the computation model and the shape of the result (three explained picks over a ranked list). Nothing an agent needs to call this correctly 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 description coverage is 85%, so the schema already documents nearly every parameter and the baseline is 3. The description adds a semantic rule the schema does not encode — pass only what the person actually said — which steers the agent away from fabricating values for the nullable budget, needs, insurers, and territory fields.

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?

Opens with a specific verb+resource ("The plan finder") and states exactly what it does: ranks every eligible VHIS plan on coverage and cost and returns three explained picks plus a ranked list. That is far more than a restatement of the name, but it never names a sibling (price_plans, compare_plans, plan_options) to draw the boundary explicitly, so an agent must infer the distinction.

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?

"Age is the only thing it needs; pass whatever else the person has actually said" is clear invocation guidance: it tells the agent the sole required input and that the remaining 12 parameters should only be populated from what the user actually stated, not invented. It stops short of saying when to prefer this over price_plans or compare_plans.

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