Pryx

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

Annotations already declare read-only and closed-world, so the safety profile is covered; the description goes well beyond it by disclosing the two-call protocol, that output is in French for the French market, and the tie semantics (tied: true, no winner elected) with an explicit instruction not to present a winner. That is behavioral context the structured fields do not carry.

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, front-loaded with the tool's output, then the invocation protocol, then the caveat. No filler, and the critical tied-behavior warning is stated last where it will be read before acting on a result.

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, the description must carry return-value semantics, and it does: verdict, French product names/explanations, and the tied case. Combined with 100% schema coverage on inputs, an agent has everything needed to invoke and interpret correctly.

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 budget and answers formats are already documented in the schema. The description only restates that the second call takes budget and answers, adding no format or constraint detail beyond the schema; 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 the Pryx verdict / which product to buy) scoped to one category, and ties itself to the sibling by naming pryx_categories as the source of the category slug. An agent can distinguish it from the category-listing sibling without opening either 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 obtain the questions, then call again with budget and answers. It also states the precondition (questions must be answered before a verdict exists) and instructs what to do when the response is tied, which is when-not guidance an agent could not infer.

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 declare readOnlyHint=true and openWorldHint=false, so safety and locality are covered. The description usefully adds that the category set is bounded to the French market, but says nothing about the shape of the returned list (names, IDs, count) or ordering.

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 short sentences, zero filler. The what-it-lists statement comes first and the caller instruction is front-loaded in second position, which is the right priority for a prerequisite tool.

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 enumeration tool with no output schema, the description supplies the domain (French market), the prerequisite role, and the constraint that advice needs a named category. Only the return-value format is unspecified, a minor gap for this simple listing endpoint.

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 no parameter semantics to add. The description correctly implies a no-argument, enumerate-everything call, consistent with the empty input schema.

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 (Lists) and resource (product categories) plus the scope constraint (Pryx buying advice, French market). An agent can distinguish this enumeration endpoint from the sibling pryx_advice tool without opening either 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?

"Call this FIRST" gives an explicit ordering rule, and the second clause explains why (advice requires a named category, never free text), which effectively routes the agent away from passing raw queries. It stops short of naming pryx_advice as the follow-up call, so it is clear but not fully explicit about the alternative.

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