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

With no annotations, the description carries the full burden. It adds behavioral context by saying 'verified deal or policy' and 'ranked,' implying results are filtered/curated and ordered. Yet it does not disclose potential limitations (e.g., data recency, market availability behavior already in schema, whether results include retailer contact info) or any side effects. For a read-only search tool this is acceptable but not rich.

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 sentences total. The first sentence is front-loaded with the primary action and result, the second gives clear, relevant usage examples. No filler, no repetition of schema fields, every phrase earns its place.

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 simple search tool with 3 params and no output schema, the description is sufficiently complete. It states the action, the result type (ranked retailers), and common use cases. It could explicitly mention that the output is a ranked list, but 'ranked' already implies that. The sibling tool names provide additional context for disambiguation. This is above the minimum viable for the tool's complexity.

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 adds value by mapping example questions to specific intents (e.g., 'free shipping' corresponds to the free-shipping enum), which helps the agent pick the right intent. It also hints at the 'country' parameter implicitly with 'where they can buy' in the schema, though the description itself doesn't mention country beyond examples. Overall, it enriches the schema's parameter docs enough to justify a 4.

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 specific verb+resource: 'Find online retailers that currently have a specific kind of verified deal or policy, ranked.' This clearly distinguishes the tool from siblings like check_retailer_trust (which likely evaluates trust of a given retailer) and lookup_retailer (which retrieves retailer details). It also provides concrete example queries ('who has free shipping', 'which stores give a student discount'), making the intent unmistakable.

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?

Usage guidance is explicit via 'Use for questions like...' followed by three representative queries that map to intent enum values. This tells the agent when to apply the tool. However, it does not explicitly mention when not to use it or name alternatives like check_retailer_trust or lookup_retailer, so it stops short of a full comparison.

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