Tabular Recipe

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds value beyond annotations by stating that no API key is needed, that the check returns one of four statuses, and that it requires a secret claimToken. This provides useful behavioral context.

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, well-structured sentence with no redundant words. Every phrase adds value (what it checks, what statuses, what's required, what's not needed).

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, but there is no output schema and the description does not explain what the output object contains beyond listing possible statuses. It also does not address error cases (e.g., invalid token, expired session). However, for a status-check tool, the provided info is moderately 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?

Schema description coverage is 0%, so the description must compensate. It mentions parameter names (sessionId, claimToken) and labels claimToken as 'secret', but offers no details on their format, origin, or constraints. For two simple string parameters, this minimal explanation is insufficient to fully guide an agent.

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 checks the status of an agent-created Stripe checkout, listing the possible statuses (pending, paid, claimed, expired). It uses a specific verb ('check') and resource ('Stripe checkout'), distinguishing it from siblings like claim_checkout or create_checkout.

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 provides basic usage context: it requires sessionId and claimToken but no API key. However, it does not specify when to use this tool versus alternatives (e.g., when to check status vs. claiming or creating), nor does it list any prerequisites or exclusions.

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 indicate non-read-only and non-idempotent behavior. The description adds crucial context: the key is a one-time return, reinforcing the need for immediate storage. This goes beyond the 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?

Two sentences with clear front-loading: the first sentence explains the action, the second provides critical usage guidance. No extraneous 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 the core action, one-time nature, and storage instruction. Lacks details on what happens if called again (likely error) and no output schema, but the description is sufficient for a simple 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?

With 0% schema coverage, the description compensates by labeling sessionId as the 'paid agent checkout' and claimToken as the 'secret claim token', adding meaning beyond the parameter names.

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 'Exchange' and resources 'paid agent checkout plus its secret claim token for a new API key'. It distinguishes from siblings like create_checkout and checkout_status by specifying the post-payment claim step.

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 context that the key is returned once and must be stored immediately, warning against repeated calls. However, it does not explicitly list when to use this tool vs alternatives like checkout_status or create_checkout.

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 read-only and open-world behavior; the description adds the critical behavioral note that credits are consumed and pricing should be checked first, going beyond the structured hints.

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 the core function, the cost warning is concise and essential.

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 covers the main behavior and cost prerequisite, but lacks explanation of return formats, error handling, and the relationship to sibling tools, especially given no output schema.

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 has 3 parameters with 0% description coverage. The description only implies the text parameter via 'recipe prose'; it does not explain the tier or theme enums, leaving semantics unclear.

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 parses recipe prose and renders the validated graph as self-contained HTML in one call, distinguishing it from the separate parse_recipe and render_recipe 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?

The description warns about credit costs and instructs to fetch /v1/pricing first, but does not explicitly state when to choose this over the separate parse/render tools or provide exclusion criteria.

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 indicate non-read-only, open-world, non-idempotent behavior. The description adds context: human approval is required in Stripe, the token is one-time and secret, and warns about exposure. This goes 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?

Three concise sentences covering purpose, returns, and security. No fluff, front-loaded, every sentence essential.

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 tool with one parameter and no output schema, the description explains what it does, the sensitive token, and the need for human approval. It lacks detail on post-approval flow (e.g., using claim_checkout) but is otherwise 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 has 0% description coverage on the bundle parameter. The description mentions 'credit bundle' as context but does not expand on the meaning of the enum values (starter, standard, bulk). It provides minimal added value.

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 creates a Stripe-hosted checkout for a credit bundle, specifying the outcome (checkout URL and claim token) and distinguishing itself from sibling tools like checkout_status and claim_checkout.

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 the tool works without an API key, and gives critical security guidance to never expose the claim token in a URL. However, it does not directly compare to sibling tools or state when to use this vs. alternatives.

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 indicate read-only, idempotent, and non-destructive behavior. The description adds valuable context: it is 'Free' and reads specific data types. No contradiction with annotations, and the description enhances understanding beyond the structured data.

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: first sentence describes the tool's core functionality, second provides a usage hint. Both sentences are purposeful and front-loaded, containing no redundant 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?

For a simple read-only tool with one optional parameter and no output schema, the description is fairly complete: it covers the main purpose and gives usage context. However, it could be more complete by explaining the return format or what 'aggregated usage' entails.

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 one parameter 'days' with clear constraints, but schema description coverage is 0% (no description in schema). The tool description does not mention the parameter 'days' at all, failing to add meaning beyond what the schema already conveys. With low coverage, the description must compensate, but it does not.

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 specific verb 'Read' and the resources involved: 'credit balance, today's allowance state, and aggregated usage'. It distinguishes itself from sibling tools like 'claim_checkout' and 'convert_recipe', which have different purposes.

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 advises 'use before a paid batch', providing clear guidance on when to invoke this tool. However, it does not mention when not to use it or suggest alternatives, which would elevate the score to 5.

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 and idempotent; description adds the credit cost behavior (free), which is beyond annotation scope. No contradictions.

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 sentence, front-loaded with purpose, no unnecessary words. Efficient.

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?

No output schema, but description lists the fields returned (name, description, color swatches, depth ramp). For a simple list tool, this is sufficient.

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?

Zero parameters; baseline is 4. No need for additional parameter info.

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 explicitly states it lists every available visual theme with specific fields (name, description, color swatches, depth ramp). Siblings are about recipes, so domain is clearly different.

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?

Mentions it's free and consumes no model credits, which is a clear usage hint. No explicit when-not-to-use, but siblings are unrelated, so no confusion.

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 the description adds valuable context: the operation costs credits and requires checking pricing first. This goes beyond the structured annotations and provides a caution about external effects, which is useful for an agent.

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, both purposeful: the first states the core functionality, the second warns about credits. No filler, front-loaded with the primary action.

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 covers the essential purpose and cost caveat, but lacks details about the output graph structure and the impact of tier choices. With no output schema and minimal parameter explanations, the context is adequate but not complete for a tool with these nuances.

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 0%, so the description must compensate, but it does not explain the 'tier' parameter or the expected format of 'text'. While 'text' is reasonably inferable from 'recipe prose', 'tier' (economy/standard) remains ambiguous, leaving a significant gap in parameter understanding.

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 opens with a specific verb ('Parse') and resource ('recipe prose'), and clearly states the output ('validated rgf/0-draft operation graph'). This distinguishes it from sibling tools like convert_recipe, which likely handles a different transformation.

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 provides a prerequisite ('fetch /v1/pricing first') and implies usage when one has recipe prose to parse, but it does not explicitly compare against convert_recipe or other siblings. This is adequate but lacks explicit alternative guidance.

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 cover read-only, idempotent, and non-destructive behavior. The description adds useful context about the output being escaped and self-contained HTML, and notes it spends no model credits, which is beyond the annotations. However, it doesn't discuss validation failure behavior or other edge cases.

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 extremely concise and front-loaded with the primary action, followed by a key cost note. Every sentence earns its place with no 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?

For a tool with two parameters (one nested object), no output schema, and strong annotations, the description covers the core function and output format but leaves gaps around theme semantics, validation specifics, and any prerequisites. It is adequate but not fully complete for an agent to invoke confidently without further information.

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 0% schema description coverage, the description needed to compensate for parameter documentation. It mentions the document is an rgf/0-draft document, which gives some context for the 'document' parameter, but it doesn't explain the 'theme' parameter at all, nor what the document object should contain. The enum values in the schema are self-explanatory only if the agent already knows what the themes look like.

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 validates and renders an rgf/0-draft document as HTML, using specific verbs and the output format. However, it doesn't explicitly distinguish from sibling tools like convert_recipe or parse_recipe, though the render-to-HTML action is distinct enough.

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 implies the tool should be used when you need to validate and render an rgf/0-draft document to HTML, but it doesn't provide explicit guidance on when to use this tool versus alternatives such as convert_recipe or parse_recipe. No exclusions or when-not-to-use criteria are provided.

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