Pryx

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, yet the description still adds real behavior: the response language is French, the tie case returns tied: true with no elected winner, and the required two-call pattern. It discloses more than the annotations alone could convey.

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 call sequence is front-loaded, followed by output obligations, the read-only note, language constraint, and the tie edge case. Every sentence carries a distinct instruction and none is redundant.

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 carries the burden and does: it describes the verdict, the productUrl field, the tied flag, and the language of the payload. Nothing an agent needs to call or correctly present results 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%, so the baseline is 3, but the description goes further by explaining that answers must be gathered from the no-answers call and that budget is supplied on the second call, giving the parameters workflow meaning the schema cannot express on its own.

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 the Pryx verdict (which product to buy) for one category — and pins down the precondition (questions answered). An agent can distinguish this from pryx_categories (slug source) and pryx_product (single-product detail) without opening any 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?

Gives an explicit two-phase protocol: call WITHOUT answers to fetch the questions, then call again with budget and answers. It also prescribes downstream behavior (always show productUrl, never present a winner when tied: true), which is unusually complete routing guidance.

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

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

Annotations already cover read-only, non-destructive, closed-world behavior, so the bar is lower. The description adds a real behavioral constraint beyond them — no free-text queries, only named categories — though it says nothing about how many categories exist or whether the list is static.

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, both load-bearing, with the ordering instruction front-loaded right after the purpose. Nothing is repeated from the title or annotations.

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 parameterless read tool with no output schema, the description covers what is returned (the category list), who it serves (the French market), and how it fits into the call sequence. Nothing an agent needs to invoke it correctly 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?

The tool takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate, and it correctly spends no space on parameter syntax.

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?

Specific verb and resource ("Lists the product categories"), plus scope (French market) and the domain constraint that Pryx gives advice per named category. It implicitly separates itself from pryx_advice and pryx_product by framing this as the category-enumeration step those tools depend on.

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?

"Call this FIRST" is an explicit sequencing instruction relative to the sibling advice tool, and the second clause explains why (advice requires a named category, never free text). An agent knows exactly when this tool must precede the others.

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

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false), so 'Read-only' is a restatement. It does add real behavioral context: result composition (best 5 offers, EUR, French market), the historical minimum and price-history summary, and the cross-tool EAN dependency. Missing details like pagination or freshness/latency are minor.

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?

Three dense sentences with the output contents front-loaded, then the EAN sourcing prerequisite, then usage triggers. Zero filler and no repetition.

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, yet the description enumerates what comes back (offers, historical low, price-history summary) plus market/currency scope and the upstream data source, so an agent has everything needed to call and interpret it.

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% for the single param, so the baseline is 3. The description reiterates that the product is identified by EAN and points at pryx_advice products[].ean, which is essentially what the schema field description already says — little added semantics beyond the structured data.

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 (returns) plus concrete resources (merchant offers, lowest price ever, price-history summary) for exactly ONE product, and pins scope with 'best 5, in EUR, French market'. This clearly separates it from pryx_advice (recommendations) and pryx_categories.

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?

Gives a clear when-to-use trigger ('answer "where is it cheapest?" or "is it a good time to buy?" after a recommendation') and a prerequisite chain ('Get the EAN from the `ean` field of pryx_advice results'). No explicit exclusions or named alternative tools are given, so it stops just short of a 5.

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