shopgraph

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

Adds significant context beyond annotations: explains _shopgraph metadata (provenance, freshness, abstain), caching behavior, credit costs. Annotations are compatible (readOnlyHint, openWorldHint).

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?

Concise single paragraph that efficiently communicates purpose, cost, and metadata; 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?

Covers all essential aspects: what the tool does, when to use, output metadata, and behavioral details. No output schema exists, but description compensates by explaining _shopgraph.

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% with detailed descriptions. The description does not add further meaning to parameters beyond what schema provides, meeting baseline expectations.

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 'Extract basic product attributes from a URL' with specific fields (name, price, brand, availability) and distinguishes from 'enrich_product' as faster and cheaper.

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 usage context: faster/cheaper than enrich_product, free tier limit, and cost per call. Does not explicitly list when not to use, but the comparison is helpful.

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?

Provides extensive detail: methodology (schema.org + LLM), costs, caching behavior, verification metadata (provenance, freshness, abstain), and confidence thresholds. Far exceeds 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?

Single dense paragraph with no fluff. Front-loaded with core purpose. Every sentence adds necessary information.

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?

Covers purpose, usage, costs, caching, output metadata. Lacks explicit list of output fields, but given no output schema, the description provides sufficient context for an agent to understand the tool's value.

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 baseline is 3. The description adds useful context like caching and cost implications for force_refresh, and explains minimum_confidence and strict_confidence_threshold behavior, adding value beyond 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 it extracts product data from raw HTML without fetching, distinguishing it from siblings like enrich_basic and enrich_product. The verb 'extract' and resource 'raw HTML' are specific.

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 mentions when to use (with scraping APIs) and implies not for fetching. Does not explicitly exclude alternatives but names sibling tools for context.

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?

Description adds significant behavioral details beyond the annotations (readOnlyHint, openWorldHint). It explains costing ($0.02/call), caching effects, field verification metadata (provenance, freshness, abstain), and the behavior of force_refresh and minimum_confidence parameters. No contradiction 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?

Description is a single paragraph of about 6 sentences, front-loaded with purpose and then details. Every sentence adds valuable information (cost, metadata, parameters). No fluff, well-structured.

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 complexity (7 parameters, no output schema), the description covers purpose, behavior, cost, and metadata. However, it does not describe the overall output structure beyond the metadata. A bit more about the response format would improve completeness, but it's still adequate.

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?

Input schema covers all 7 parameters with descriptions, so baseline is 3. Description adds extra context: cost implications for force_refresh (3x credits) and minimum_confidence (2x on refresh, 0.25x on cache hit), and explains the meaning of output metadata fields. This adds value beyond the 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?

Description clearly states the tool extracts comprehensive product data from a URL, listing specific fields (name, price, brand, etc.). This distinguishes it from sibling tools like enrich_basic and enrich_html which likely have different scopes. The verb 'extract' and resource 'product data from URL' are specific.

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?

Description provides cost and caching behavior, and mentions schema.org/LLM fallback, which helps understand when it works best. However, it does not contrast with sibling tools (enrich_basic, enrich_html) or give explicit when-to-use versus alternatives. The usage context is implied but not explicit.

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 declare read-only safety and external URL access; description adds valuable behavioral context by detailing the five scoring dimensions and confirming 'Full scoring breakdown included' in output. Does not explain payment_method_id integration 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?

Three tightly-constructed sentences with zero redundancy. Front-loaded with primary action (extract and score), followed by evaluation criteria, and output characteristics.

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?

Compensates well for missing output schema by specifying return type (score 0-100) and detailed breakdown inclusion. Addresses core complexity (4 params, open-world access) but could clarify payment integration point.

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?

With 100% schema coverage, baseline is 3. Description mentions 'UCP compatibility' which semantically anchors the 'ucp' format option, but does not elucidate the unusual payment_method_id parameter or strict_confidence_threshold behavior.

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-resource combination ('Extract product data and return agent-readiness score') combined with distinct scope (scoring 5 specific dimensions). The scoring focus clearly differentiates it from enrichment siblings.

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?

Implies usage context through specific scoring criteria (agent-readiness, UCP compatibility), but lacks explicit guidance on when to prefer this over enrich_product or enrich_basic for data extraction tasks.

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