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

Annotations already declare read-only, non-destructive, closed-world, so safety is covered; the description adds market scope (French market, EUR), a result ceiling (best 5 offers, up to 3 alternatives) and the derived fields it returns. It does not cover behavior for an unknown/missing EAN or any latency/rate considerations, which keeps it below a 5.

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 the return payload and kept to three sentences with no filler. The first sentence is a long enumerated run-on, which slightly hurts scannability, but every clause (currency, market, caps) carries useful information.

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?

There is no output schema, so the description must characterize returns, and it lists all the major components (offers, all-time low, history summary, priceAdvice, alternatives with reason). It stops short of return structure or failure behavior, but nothing needed for correct invocation 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 coverage is 100% and the schema already documents `ean` as EAN/GTIN digits sourced from pryx_advice products[].ean. The description's pointer to the `ean` field is a small reinforcement of sourcing, not new semantics, so 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?

States a specific verb and resource (returns merchant offers, price history, priceAdvice, alternatives for ONE product by EAN) and enumerates the payload, so it is clearly distinguishable from pryx_advice (recommendations) and pryx_categories. An agent knows exactly what it gets 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?

Explicitly says where the EAN comes from (the `ean` field of pryx_advice results) and names the two caller intents it serves, 'where is it cheapest?' and 'is it a good time to buy?', sequenced after a recommendation. That is when-to-use plus a dependency, not just implied usage.

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