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

Annotations already declare readOnlyHint, idempotentHint, non-destructive. The description adds valuable behavioral details: returns FDA indications, denial reasons, appeal arguments, step-therapy framing, and external review record. This extra context helps the agent understand the tool's scope beyond safety.

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?

Three sentences with front-loaded key information. The list of drug names is somewhat lengthy but relevant. Could be slightly more concise by grouping, but overall efficient and clearly structured.

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?

Given no output schema, the description adequately explains the return value: FDA indications, denial reasons, winning appeals, step-therapy exception, and external review record. It covers key aspects but could mention ordering or that results are in text/structured form.

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% with a clear description for the single parameter 'drug'. The description's mention 'Accepts a brand or generic name' is redundant with the schema. No additional parameter semantics are provided, so score at baseline 3.

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?

The description clearly states it returns drug-specific denial patterns and appeal strategies, listing specific drug classes (GLP-1s, IBD biologics) and what it provides (FDA indications, denial reasons, winning appeals, step-therapy, external review). It distinguishes itself from siblings like get_appeal_rights (general appeal rights) and get_condition_outcomes (outcomes) by focusing on the denial playbook for high-friction medications.

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 description implies use for medications 'plans fight hardest over' and names specific drugs, providing clear context. However, it does not explicitly state when not to use it or give alternatives among siblings. The agent can infer its niche from sibling names, but explicit guidance would improve.

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