search_amazon_alexa

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

There are no annotations, so the description carries the entire burden and does so thoroughly: point cost (6 per prompt, N×6), a 120-second client-side timeout requirement, an explicit warning against concurrent duplicate calls, the distinction between the native HTTP path and the slower browser screenshot path, and the caveat that products and suggestions may be empty. It also discloses that context is shared only within a single call, which materially affects how an agent should batch prompts.

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 purpose before the labeled Use when / Returns / Cost / operational blocks, and each block is a single dense sentence. It runs long, but on a tool with no annotations and no output schema nearly every line carries information an agent needs; only the returns-format block slightly duplicates what the schema's nested field naming implies.

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?

With no output schema and no annotations, the description fills both gaps: it sketches the return shape (prompt, content, products with nested items, follow_up_questions), warns results may be empty, and covers cost, latency, concurrency, and market-pool behavior. Nothing an agent needs to invoke this correctly or set expectations 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 100%, so every parameter already carries its own documentation, including the pool-isolation failure mode, the 1–5 prompt limit, per-prompt cost, and the screenshot path. The description largely restates the same facts rather than adding new meaning such as prompt phrasing guidance or examples, so the baseline 3 applies.

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 first sentence names a specific verb and mechanism (ask Amazon Rufus) and enumerates the concrete outputs: answers, grouped product recommendations, follow-up suggestions. It also frames the scope boundary (US vs Japan pools), and the 'Use when' clause explicitly distinguishes it from search_amazon and get_amazon_product, so an agent can separate it from all three siblings without opening a 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?

Explicit when-to-use is given ('scenario-based discovery, gifts or open-ended shopping advice') paired with named alternatives and the condition that selects each ('search_amazon for explicit keywords', 'get_amazon_product for a single ASIN'). This is the full when/when-not/alternative pattern rather than an implied context.

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