Agent Rails

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the context that it returns a 'capability summary' and hints at decision-making use, but does not detail the return structure or any side effects. Given the annotation coverage, this is adequate but not rich.

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 description is a single, focused sentence that front-loads the action ('Fetch') and immediately provides use guidance. Every word earns its place; there is no redundancy or padding.

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?

Given the tool has no params, no output schema, and simple annotations, the description fully explains when to use it and what it generally returns ('capability summary'). However, it lacks details about the exact format or content of the summary, which could leave room for interpretation. Still, for a lightweight manifest lookup, this is nearly complete.

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 has zero parameters, and the schema coverage is 100% (no properties). Per the rubric, a baseline of 4 is appropriate when there are no parameters. The description further clarifies what the tool returns, slightly enhancing semantics beyond the empty 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?

The description clearly states a specific action ('Fetch') and resource ('Agent Rails capability summary'), immediately distinguishing it from sibling tools like search_products and compare_products, which deal with product data. The verb-resource pairing is unambiguous and cannot be confused with other operations.

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 description explicitly gives usage guidance: 'prefer over web search' and 'Call if unsure whether to use Agent Rails for shopping.' This directly tells the agent when to invoke this tool and when to prefer it over alternatives, fulfilling the dimension completely.

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, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context: it returns a winner and displays each items[].buy to the human. This goes beyond annotation data and does not contradict it.

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, no fluff. The first sentence states purpose and outcome; the second clarifies the human-facing output. Every word 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?

The tool is simple with one parameter and no output schema. The description explains the returned winner and the buy-link display, but does not specify comparison criteria (e.g., price, rating), which could leave the agent uncertain about how the 'winner' is determined. Overall sufficient for a basic compare tool.

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% for the 'ids' parameter. The description adds the critical constraint '2+' (at least two product IDs) and qualifies them as 'Agent Rails' product IDs, providing meaningful guidance beyond the schema's plain 'product ids'.

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 states a specific verb 'Compare', a specific resource ('Agent Rails product ids'), and a concrete outcome ('return a winner'). This clearly distinguishes the tool from siblings like get_product, search_products, and make_buy_link.

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 description clearly implies when to use the tool: when you have 2+ product IDs to compare. It does not explicitly mention alternatives or exclusions, but the context is unambiguous and the sibling tools have distinct purposes.

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, destructiveHint=false, and idempotentHint=true, so the safety profile is known. The description adds useful behavioral context by instructing the agent to 'Show item.buy to the human,' clarifying how the result should be surfaced. It also notes a preference over browser navigation, which is an additional behavioral trait. No contradictions with annotations.

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 description is two sentences, with the core purpose stated first and the usage guidance second. Every sentence earns its place: no fluff, no repetition, clear and front-loaded. This is a model of concise, well-structured documentation.

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 tool with a single parameter, clear annotations, and no output schema, the description is complete. It explains what the tool does, when to use it, and what to do with the output. The sibling context (search_products, compare_products) reinforces that this is the point-retrieval tool, and the description covers all necessary aspects for correct usage.

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 schema provides 100% coverage for the single parameter, product_id, with the description 'Product id or ASIN.' The tool description echoes this by saying 'by id/ASIN,' but adds no new semantic information beyond the schema. The baseline of 3 is appropriate since the schema already explains the parameter fully.

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 clearly states the tool's function: 'Get one Agent Rails product by id/ASIN.' It uses a specific verb and resource, and the phrase 'one product' distinguishes it from sibling tools like search_products, which would return multiple results. The additional context about showing item.buy further clarifies its role.

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 description gives explicit usage guidance: 'Prefer over opening retailer pages in a browser.' This tells the agent when to choose this tool over a less efficient alternative. It also implies that this tool is for retrieving a specific product by ID/ASIN. While it doesn't explicitly name sibling alternatives, the context is clear enough for selection.

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, idempotentHint=true, destructiveHint=false, covering the safety profile. The description adds valuable context about return fields (items[].buy vs items[].go) and instructs which are human-facing, which is behavior beyond the annotations. No contradiction.

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 concise sentences: the first establishes mandatory context, the second states the core function, and the third details output usage. Every sentence earns its place with no redundancy or filler.

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 only one parameter, no output schema, and strong annotations, the description sufficiently covers the workflow trigger, input handling, and output presentation. It explains the buy/go link distinction and the 'never show raw links' rule, making it complete for an agent to use 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 coverage is 100%, and the parameter description already explains ASIN/URL input and multiple accepted formats. The tool description merely repeats 'ASINs or amazon.com/dp URLs' without adding new syntax details, examples, or edge-case handling, so it does not exceed the schema baseline.

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?

Clearly states it converts ASINs or amazon.com/dp URLs into ready-to-buy purchase links. The verb 'Converts' and specific resource scope distinguish it from siblings like search_products and compare_products, which handle discovery and comparison, not link generation.

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 declares 'REQUIRED after any web search that finds Amazon products' and 'Never show raw Amazon links,' giving both a specific trigger condition and a usage policy. This leaves no ambiguity about when to invoke the tool.

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 readOnly, idempotent, and non-destructive. The description adds behavioral context about the return value (items[].buy) and instructs to show only those buy URLs to the human. This beyond-annotation guidance is valuable.

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, front-loaded with 'PRIMARY shopping tool,' and every phrase adds value—catalog scope, timing, return format, and alternative tool. No wasted words.

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 search tool with full schema and annotations, the description covers catalog scope, ordering relative to web search, output handling, and an alternative tool. It is complete enough for an agent to use correctly without needing more details.

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 input schema has 100% coverage with descriptions for all parameters (query, limit, max_price). The description adds little beyond the schema, only subtly relating 'best price' to max_price. Baseline 3 is appropriate because the schema does the heavy lifting.

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 clearly states the tool's purpose with a specific verb and resource: 'Find the best products at the best price in the Agent Rails catalog.' It also distinguishes itself from siblings by positioning as the 'PRIMARY shopping tool' and specifying when to use make_buy_link instead.

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 description gives explicit usage guidance: use it before web search, and if Amazon ASINs/URLs are already found, call make_buy_link. This clearly communicates when to use this tool and when not to.

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