Corbelworks Agent Reliability

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

Annotations declare readOnlyHint=true, so no mutation. Description adds that the link receipt records payment_status=not_paid, which is useful context but does not contradict annotations. The bar is lower due to annotations, and description adds some beyond but not extensive.

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 the key action and cost. No fluff, though could add parameter guidance without much length.

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 has an output schema (not shown) and one optional parameter. Description covers the main output (checkout link, receipt status) but lacks explanation of the parameter and any prerequisites or post-actions. Adequate but not thorough.

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 only parameter (workflow_summary) has 0% schema description coverage, and the description does not explain its purpose or usage. This leaves the agent without guidance on what to provide or how it affects the result.

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 returns a fixed $149 Stripe checkout link for a specific scan, with a receipt recording payment_status=not_paid. It distinguishes from sibling tools (reliability_preflight, verify_action_receipt) by indicating this is the purchase 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?

No guidance on when to use this tool versus siblings like reliability_preflight or verify_action_receipt. No prerequisites or excluded scenarios mentioned.

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 provide readOnlyHint=true, and the description adds that it 'returns a signed Corbelworks action receipt', giving output context. 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?

Single sentence, front-loaded with action and result. 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?

Output schema covers return values, but parameter is not explained despite 0% schema coverage and nested object complexity. Lacks error conditions or required claims structure.

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 0%, yet the description adds no meaning about the manifest parameter or its claims structure. The description only mentions 'agent claims' without specifying format or expectations, leaving a significant gap.

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: 'Find false-green risk by linting agent claims against evidence, freshness, and external-receipt requirements'. It implies a preflight check, distinguishing it from siblings like 'purchase_agent_reliability_scan' and 'verify_action_receipt', but does not explicitly differentiate.

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?

No guidance on when to use this tool versus alternatives. Siblings exist but no context for when to choose this over purchase_agent_reliability_scan or verify_action_receipt.

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 readOnlyHint, idempotentHint, and non-destructive, which match the verify action. Description adds that it verifies against a published public key and specifies Ed25519, providing useful 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?

Single sentence with 13 words, directly states the action with no superfluous information. Front-loaded and 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?

Given low parameter count and existing output schema, the description is acceptable but lacks usage guidelines and detailed parameter semantics. It is adequate but not comprehensive.

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 sole parameter 'receipt' is an object with no schema description (0% coverage). The description implies the receipt contains payload digest and signature, adding some meaning, but does not fully specify the expected structure or any subfields.

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 'verify', the resource 'action receipt', and specifics (Ed25519, payload digest, signature, published public key). It distinguishes from siblings which are about reliability scans.

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?

No guidance on when to use this tool vs alternatives, no prerequisites, and no mention of when not to use. The description lacks contextual usage hints.

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