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

Annotations already cover read-only, idempotent, and non-destructive hints. The description adds substantial behavioral context: the offer matrix structure, observedAt dates, the savingsCard field (including when it might be missing), the isLowest flag, and explicit guidance on how to interpret and present results. This goes well beyond the annotation safety profile and gives the agent operational rules.

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 description is front-loaded with the core purpose, then adds usage context, return structure, and behavioral rules in a logical order. Every sentence contributes – none are redundant. It's long but dense with necessary operational guidance, and the key info (purpose, when to use) appears early. No fluff or filler.

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 the tool's moderate complexity and that an output schema exists, the description is quite complete. It explains the return structure (offer matrix, savingsCard, isLowest) and provides instructions on how to use the results. The main gap is the lack of explanation for locale and channel parameters, though they have defaults and are likely non-critical. For the required parameters and the output interpretation, it's thorough.

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%, so the description must compensate. It does clarify the ndc format ('11-digit NDC') and the quantity, and advises where to obtain an ndc. However, it does not mention the optional locale and channel parameters, which have defaults but still remain undocumented. Since two of four parameters are unexplained, the description only partially compensates for the missing schema descriptions.

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 opens with a precise verb+resource: 'Compare FineRx prices for one package (an 11-digit NDC + quantity).' It clearly distinguishes from siblings by specifying the input condition ('Use when you know the exact package') and referencing how to obtain the NDC (from get_drug or search flow), making it unambiguous what this tool does versus alternatives.

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 states when to use ('Use when you know the exact package') and directs the agent to get the NDC from get_drug or the search flow, implying when not to use it. It also adds concrete rules: don't call a price lowest unless isLowest, always give the observation date, and offer the card when quoting a price – these are precise usage conditions that prevent misuse.

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