HTTP 402 AI Tollbooth

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

With no annotations, the description carries the full burden and does disclose the single most important behavioral trait: this call does not initiate or pay a transaction, i.e. it is a safe non-mutating read despite the "buy" name. It stops short of stating auth requirements, side effects, or what the directions look like.

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?

A single sentence with no filler, front-loading the actual behavior and the critical non-mutation disclaimer. Every clause earns its place.

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 one-parameter tool with no output schema, the description establishes purpose, safety profile, and the source of the product ID (via the schema). Return content is only loosely characterized as "directions," which is a minor gap but adequate given the tool's simplicity.

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?

Only one parameter with 100% schema description coverage; the schema already explains it is a kebab-case product ID from list_products. The description adds no further parameter meaning, so the baseline of 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 resource and outcome ("purchase directions for a product") and immediately negates the misleading implication of the name by saying it does not initiate or pay a transaction. It distinguishes itself from a real purchase action, though it does not contrast with siblings like preview_product or list_products by name.

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 negative clause ("without initiating or paying a transaction") implies the usage context — retrieve instructions rather than execute a purchase — but it never states when to prefer this over preview_product or list_payment_methods, or any prerequisite. Usage is inferable rather than stated.

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?

With no annotations, the description carries the full behavioral burden. It does disclose the scoping filter ('currently enabled', i.e. disabled rails excluded) and hints at return content ('public machine-readable contracts'), but says nothing about authentication, caching, or the actual response shape for what is presumably a safe read.

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?

A single front-loaded sentence with no filler; every phrase ('currently enabled', 'machine-readable contracts') contributes meaning.

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 zero-parameter, annotation-free read tool with no output schema, the description covers the essentials of what is listed and how it is scoped. It could say a bit more about the response format, but the gap is minor given the tool's simplicity.

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 schema needs no compensating description and the baseline of 4 applies. The description correctly adds no parameter detail because there is none to add.

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 gives a specific verb ('List') and resource ('currently enabled payment rails and their public machine-readable contracts'), so an agent can tell it apart from the product-oriented siblings. It stops short of explicitly contrasting itself with list_products or buy_product, so it earns a 4 rather than a 5.

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?

Usage is only implied: an agent needing payment options would call this, but the description never states when to use it, when not to, or how it relates to the sibling tools in the purchase flow. No explicit routing or prerequisites are given.

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?

With no annotations, the description carries the full disclosure burden. It partially meets this by stating the returned fields, which implies a read-only catalog read, but it says nothing about pagination, result limits, authentication scope, or whether 'all' really means unscoped.

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?

A single front-loaded sentence with no filler. The trailing enumeration of fields is slightly list-heavy and the phrase 'endpoint paths' is cryptic for a product listing, keeping it just short of a 5.

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 zero-parameter tool with no output schema, the description usefully enumerates the returned fields, which is the main missing piece structured data would normally supply. Only pagination/scope behavior remains uncovered, a minor gap for such a simple read.

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 of 4 applies; there is nothing for the description to clarify beyond confirming no filtering input is accepted, which 'List all products' implicitly does.

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 gives a specific verb ('List') plus the resource ('products') and enumerates the returned facets (categories, tiers, prices, item counts, endpoint paths). This is enough for an agent to distinguish it from buy_product and preview_product, though it never names those siblings to reinforce the contrast.

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?

There is no when-to-use or when-not-to-use guidance, and no alternative is referenced despite three plausible siblings (buy_product, preview_product, list_payment_methods). The browse-the-catalog use case is only weakly implied by the verb 'List'.

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?

No annotations are provided, so the description carries the full burden. It usefully discloses result cardinality ('exactly three') and that the samples are free, but says nothing about auth requirements, what a sample record contains, or behavior for an invalid product ID.

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?

One short sentence with no filler, front-loading the action and the cardinality constraint. Nothing is redundant or buried.

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 one-parameter read tool with no output schema, the description should ideally describe the shape of a returned sample and any failure mode; it only conveys the count and cost. Adequate but with clear gaps.

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% and the single 'product' parameter is fully documented as a kebab-case ID from list_products. The description adds no format or sourcing detail beyond the schema, so the baseline of 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 concrete verb and result ('Get ... sample records') with a scope ('exactly three free') and a timing cue ('before purchase') that separates it from buy_product. It never names the product resource explicitly, so the agent must infer that it previews the product passed in, but the intent is still legible 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?

'before purchase' implies the evaluation scenario in which this tool is used and contrasts with the buy step, but no sibling is named and there is no explicit 'use this instead of X' or exclusion condition. Usage is only implied.

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