Misfit Machine Store

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

Annotations already declare readOnlyHint=true and destructiveHint=false; description adds the specific non-actions (does not create checkout, cart, order, etc.) and frames it as 'read-only detail retrieval', reinforcing the idempotentHint. It doesn't mention rate limits or auth beyond the UCP profile mention which is in schema, but adds enough context beyond 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 a single, front-loaded paragraph (approximately 60 words) that states the purpose, the when-to-use, and the boundary of what it does not do. Every sentence adds value and there is no redundancy with the schema.

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 there is an output schema and the annotations disclose read-only/idempotent behavior, the description covers the essential prerequisites (requires 'meta.ucp-agent.profile', 'catalog.id') implicitly via schema, and explicitly states the side-effect-free guarantee. It doesn't explain error conditions or rate limits, but those are not required for high completeness. The missing negative guidance on when NOT to call it (e.g., for multi-product or mutation) is implied by 'exactly one selected product' and the non-actions.

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 has thorough parameter descriptions (100% coverage), including the purpose of each field and clarifications like 'no purchase occurs' and 'never authorizes billing.' The tool description adds little beyond pointing to the schema's 'exactly one selected product' requirement and id source. Given the high schema coverage, the description doesn't need to add much; baseline of 3 is appropriate.

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?

Description states a specific verb ('read-only detail retrieval') and resource ('exactly one selected product'), and explicitly distinguishes from sibling tools by naming them and the sequencing ('Call after search_catalog or lookup_catalog'). It also enumerates what it does NOT do (create cart, order, etc.), making its scope unmistakable.

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?

Provides explicit when to use: after search_catalog or lookup_catalog, when full current price, availability, machine endpoint, and checkout-handoff metadata are needed. Also specifies a clear when-not by listing side-effects it does not produce (create checkout, cart, order, payment, credential, merchant state).

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?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description reinforces these with 'Read-only' and 'No purchase or mutation occurs,' which adds a small amount of context beyond the annotations. However, it does not mention potential errors, rate limits, or other side effects that might affect caller behavior.

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 long, starts with the core purpose ('Read-only identifier lookup'), and packs all necessary guidance without fluff. It front-loads the action and resource, then provides usage and alternatives in a compact, scannable manner.

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 simple identifier lookup tool, the description provides sufficient context: it explains what data is returned (price, availability, machine endpoint data), when to use it, and how it differs from siblings. It does not describe the output schema, but the presence of an output schema (as indicated in context) means that is not required. The description is slightly generic about optional parameters but still gives a complete picture for an agent.

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 provides descriptions for all parameters (ids, context, filters, signals, attribution), achieving 100% coverage. The tool description does not add much beyond what the schema states; it repeats the types of identifiers and mentions the return intent, but does not clarify the meaning or purpose of the optional parameters. Since coverage is high, a baseline of 3 is appropriate.

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 verb ('lookup') and resource ('catalog'), and specifies the exact use case: retrieving current price, availability, or machine endpoint data for known product, variant, SKU, or handle IDs. It also names sibling tools directly, distinguishing itself from search_catalog (unknown IDs) and get_product (single item full detail).

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 tells when to use this tool: 'Call this when you already have one or more product, variant, SKU, or handle IDs and need current price, availability, or machine endpoint data.' It also gives clear alternative instructions: 'Use search_catalog if IDs are unknown; use get_product for full detail on one selected item.' This leaves no ambiguity.

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?

Explicitly states it is read-only, returns matching products with price, availability, and endpoint metadata; clarifies no cart, checkout, order, payment, credential, or merchant mutation occurs. Annotations (readOnly=true, idempotent=true, destructive=false) align with the description, so no contradiction. This is a model of behavioral transparency.

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 concise but informative, using clear bullet-style clauses. The schema is well-structured with nested objects and clear descriptions. The additional text explaining when to call and what does not happen is efficient and not verbose.

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 description provides full context: it states read-only semantics, what the tool returns, what it doesn't do, and how it fits into a workflow (use lookup_catalog when IDs are known, get_product after selecting). It covers usage scenarios shortages (like knowing product ID) and highlights non-mutations. The schema explains required fields and optional fields. This is highly 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 schema provides detailed descriptions for each parameter: meta explains it's for capability negotiation and is read-only; catalog describes its role as a search request with query, context, filters, signals, and pagination. The 'query' parameter has examples and pagination has min/max and descriptions. The schema description coverage is 100% per the metadata, and the description provides additional examples and clarifies optional fields. Parameters are well-documented.

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?

Title and description clearly state the tool's purpose: searching Misfit machine products. It explicitly mentions it is read-only product discovery and says to call it first when the product ID is unknown, with clear next steps (lookup_catalog, get_product).

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?

Provides strong usage context: call this when product ID is unknown, use lookup_catalog when IDs are known, and use get_product after selecting a product. Also explains the purpose of the tool in the discovery flow, making usage guidelines excellent.

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