firestarter_preview

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

Read-only behavior is already captured by annotations, but the description adds valuable specifics: 'nothing is bought and no approval is created', options are 'live', and results distinguish buyable vs browse-only products. This goes beyond the annotation's simple readOnlyHint and gives the agent a clearer behavioral model. No contradiction.

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 three sentences and every sentence earns its place: purpose and non-destructive guarantee, return-value highlights, and the usage framing with firestarter_execute. It is front-loaded with the most important fact (no purchase starts) and contains no 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?

For a tool with 10 parameters, a nested context object, and an output schema, the description covers purpose, safety, eligibility semantics, and the relationship to firestarter_execute. Pagination and currency-display behavior are already documented in the parameter schema, so the description does not need to repeat them. Minor missing piece: it could more explicitly mention paging through large result sets, but the schema handles that.

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 100%, so the baseline is 3, but the description adds meaning by linking the eligibility outputs to the relevant parameters: 'in budget, can arrive by the deadline, and ships to the destination' maps to max_price, deadline, and city/country. This helps the agent understand how those parameters influence the returned options beyond their individual field 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 states a specific verb, resource, and scoping constraint: 'Preview real products for a natural-language request WITHOUT starting a purchase.' It explicitly names the purchase counterpart, firestarter_execute, and clarifies that this tool is the read-only pre-purchase view, so an agent can distinguish it from siblings without opening the schema.

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 gives clear usage context: use this to answer 'what can you get me?' and as the step 'before any purchase starts (firestarter_execute)'. It names the closest alternative, firestarter_execute, and implies this tool should be called before committing. It does not explicitly address broader catalog-search alternatives, but the guidance is strong.

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