IntentFence Agent Action Firewall

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

Annotations already indicate read-only behavior. The description adds that it is 'metadata-only' and does not execute tools, consistent with annotations. It does not mention auth needs or rate limits, but the read-only nature is clear.

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 concise sentences; the first states the core function, the second adds critical limitations. No unnecessary words. 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 purpose and limitations but omits what the tool returns (e.g., a list of findings). Given no output schema, the agent needs to know the format or structure of the scan result. This is a notable gap.

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 must compensate but only provides high-level context ('caller-supplied MCP tool definitions' for the 'tools' parameter). It does not explain individual parameters (server_name, tools) in detail, leaving an agent to infer from context.

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 action ('scan') and the resource ('caller-supplied MCP tool definitions'). It lists specific items checked (missing schemas, unsafe annotations, etc.), distinguishing it from sibling tools that focus on authorization or policy packs.

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 when to use this tool (to validate tool definitions) and includes a notable limitation ('does not execute tools or certify security'). However, it does not explicitly state when to use alternatives or provide exclusions, leaving some room for improvement.

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 mark readOnlyHint=true, so the description adds value by stating 'never executes the downstream action' and revealing the receipt validity (five-minute ES256). It also implies the tool is safe for repeated calls (no side effects). 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 three sentences with no redundant phrasing. It front-loads the core purpose and immediately follows with critical behavioral constraints. Every sentence adds unique value without repeating schema or annotations.

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 (5 params, nested objects, no output schema), the description covers the tool's purpose, key constraints, and post-call verification. It lacks explicit output structure, but the mention of a 'five-minute ES256 receipt' implies a signed token, which may suffice for agents. The instructions to 'fail closed' add practical completeness.

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%, so the description must compensate. It provides high-level mapping: 'exact agent action' (action param), 'explicit allowlist, spend ceiling, retention ceiling' (policy param), and 'optional action-bound approval' (approval param). However, it omits explanation of subject and context parameters, and the nested action structure is not detailed. This is adequate but incomplete.

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 uses specific verbs ('authorize an exact agent action') and clearly identifies the resource being operated on (allowlist, spend ceiling, retention ceiling). It distinguishes itself from sibling tools like intentfence_agent_risk_scan and intentfence_preflight by emphasizing authorization against explicit policies rather than risk assessment.

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 states the tool never executes the downstream action and provides clear post-call instructions: callers must verify the receipt and fail closed if the action changes. This tells agents exactly when and how to use this tool (before execution) and what to do with its output.

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 read-only, idempotent, non-destructive. Description adds that it never signs or initiates payment and lists outputs, aligning with and enhancing annotation 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?

Two concise sentences, front-loaded with key outputs and a clarifying behavioral note. No redundancy.

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, outputs, and safety. With no output schema, could specify return format more, but still adequate for selection and invocation.

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%. Description explains 'select a paid outcome' for product and notes omitting input yields an example recipe, adding meaning 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 specifies the tool as a 'Free machine checkout builder' that selects a paid outcome and returns endpoint, request, etc. It clearly distinguishes from sibling product-specific tools.

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?

States to 'Select a paid IntentFence outcome' and clarifies it never signs or initiates payment, implying use for preparing checkout. Does not explicitly mention alternatives or when not to use.

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 and openWorldHint, which are consistent with the description. The description adds behavioral context: paid (1 USDC on Base), generates artifacts (non-destructive), and requires no meeting or account. This goes beyond annotations by revealing the cost and ease of use.

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: first states the purpose and cost, second adds runtime details and condition. Every sentence carries meaning with 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?

Given the complex nested schema (3 parameters with deep objects) and absence of an output schema, the description provides a list of generated outputs but does not explain input semantics beyond runtimes. It partially covers what the tool does but leaves gaps in parameter understanding.

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 only 33% (only project_name has a description). The description mentions runtimes ('Cloudflare Agents, Coinbase AgentKit, or an MCP gateway') but does not detail the complex authorization object or its nested fields. As a result, the description insufficiently compensates for the low schema coverage.

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 generates a runtime-specific TypeScript guard, signed action and policy receipt, negative test vectors, and a fail-closed deployment checklist for specific runtimes. The verb 'generates' and resource 'policy pack' are specific, and it distinguishes itself from sibling tools by focusing on policy pack 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?

The description provides no explicit guidance on when to use this tool versus siblings like intentfence_authorize_action or intentfence_preflight. It only mentions 'No meeting or account is required' as a convenience, but does not clarify use cases or 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 declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds that it has no authorization proof or enforcement guarantee, which are behavioral traits beyond what annotations capture. 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?

Two sentences, front-loaded with key distinctions (free, no guarantees, return types). No unnecessary words; each clause adds value.

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 4 parameters, nested objects, and no output schema, the description lacks details on parameter meaning, usage scenarios, and expected results beyond the three labels. Leaves significant gaps for effective tool invocation.

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 only 25% (only subject has a description). The tool description does not mention any parameters or explain the nested 'action' or 'constraints' objects. For a tool with 4 parameters including nested objects, this is insufficient.

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's a 'Free declared-input preview' that returns three categorical outcomes. This differentiates it from siblings like 'verified_preflight', though not explicitly. The verb 'preview' and resource 'declared-input' 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?

The description implies lightweight, non-authoritative use via 'no signed receipt, authorization proof, or enforcement guarantee'. However, it does not explicitly state when to use versus alternatives or provide 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 mark the tool as readOnly=true and destructive=false. The description adds behavioral info: it costs $0.001 USDC, has a six-hour cache, and returns a provenance receipt. 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?

Two sentences efficiently convey cost, source, cache behavior, receipt format, and optional parameter. Front-loaded and 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?

Given no output schema, the description implies return of CPI data and a receipt but could explicitly state response structure. The cost and cache detail add value, but a clear statement of what the response contains (e.g., CPI values, timestamps) is missing.

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 single parameter 'month', with a clear pattern and description. The description merely restates 'Optionally request a YYYY-MM period', adding no new semantics 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?

The description clearly states the tool provides official U.S. CPI data, retrieval source, cost, and provenance. It is distinct from all sibling tools which deal with risk, authorization, and assessments.

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 explains the optional month parameter and implies usage for CPI data. However, it does not explicitly state when not to use or mention alternatives among siblings, which are unrelated anyway.

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?

Adds value beyond annotations by disclosing the cost ($0.005), settlement method (x402), and output (signed receipt and metadata). However, does not mention that the call is not idempotent or that repeated calls incur additional cost, though annotations indicate non-idempotency.

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 packs essential information but is dense. Could be slightly more structured to aid readability.

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?

Despite being a complex tool with nested parameters and no output schema, the description omits many details needed for correct usage, such as parameter meanings, constraints purpose, and the exact return format beyond a receipt.

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?

Description provides no explanation for any of the 4 parameters (subject, action, proofs, constraints). With only 25% schema coverage, the description fails to compensate, leaving the agent with minimal guidance on how to construct the input.

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 is a paid production preflight with specific cost and returns an audit receipt and metadata, distinguishing from free or unverified preflights. However, does not explicitly contrast with sibling 'intentfence_preflight'.

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 explicit guidance on when to use this tool versus alternatives like 'intentfence_preflight'. The cost implication is mentioned but not contextualized.

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?

Discloses cost ($0.002), blockchain (Base), checks performed (GoPlus sanctions, etc.), receipt type (ES256, 5-minute), and a disclaimer about what low-risk does not prove. Annotations mark it read-only; description confirms non-destructive 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 sentences, front-loaded with key information (cost, purpose), efficient and no wasted words. Every sentence adds value.

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 read-only screening tool with one parameter and no output schema, the description covers purpose, inputs, checks performed, output format (ES256 receipt), and limitations. Only minor gap: exact format of receipt output is not described, but the tool is sufficiently 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?

Input schema has 100% description coverage for the single parameter. The description adds no new parameter details but reinforces the context (Base address). Baseline 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 this is a paid AML/KYT wallet screening tool for use before sending funds or approving a transaction on Base. It distinguishes itself from sibling tools like intentfence_agent_risk_scan by focusing on wallet-specific risk assessment.

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 states usage context ('before sending funds or approving a transaction'), providing clear guidance on when to invoke. Does not explicitly exclude scenarios or name alternatives, but the context is sufficient.

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=true and no destructive effects. The description explains the tool validates without contacting the target and returns a short-lived receipt. It also mentions the validation scope (quote, asset, price ceiling, etc.). This aligns with annotations and adds transparent behavioral details.

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. The first sentence front-loads the main action and outcome. The second sentence provides critical parameter guidance. No redundant or filler content.

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 complex (5 parameters, nested object, no output schema). The description explains the core functionality and key parameter behavior but omits details about the output format (receipt structure), error conditions, and payment confirmation. With no output schema, more context on the return value would improve completeness.

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 60% (some parameters have descriptions). The description adds unique value by explaining the effect of including 'allowed_payees' (safe_to_proceed vs. needs_review) and the requirement to forward the exact base64 header. This goes beyond the schema's static descriptions.

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 performs a paid assessment by validating an x402 quote and returning a receipt. It specifies the exact operation: forwarding the PAYMENT-REQUIRED header, validating against policy, and returning a bound receipt. The purpose is distinct from siblings like 'intentfence_x402_readiness', which likely checks readiness before payment.

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 guidance on the 'allowed_payees' parameter: supplying it yields 'safe_to_proceed', omission yields 'needs_review'. This tells the agent when to include it. However, it does not provide when to use this tool versus siblings or list alternative tools.

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 (readOnlyHint: true, destructiveHint: false) already indicate safe read behavior. The description adds critical context: it makes a paid request ($0.002 USDC), blocks private networks and redirects, never pays the target, validates the x402 challenge, and returns a signed receipt. 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?

Single sentence with no wasted words, front-loaded with cost and action. Every clause 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?

Despite no output schema, the description covers the full process: request, constraints, validation, and output (receipt). Minor gap: receipt format not specified, but overall complete for a tool with good parameter documentation.

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 86%, so baseline is 3. The description does not add parameter-level details beyond the general tool flow; the schema already documents parameters well.

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 uses a specific verb ('Paid live endpoint check') and clearly identifies the resource (HTTPS target with x402). It distinguishes from siblings like 'intentfence_x402_assessment' by detailing the bounded, credential-free request and receipt 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?

The description implies use for readiness checking but does not explicitly state when to use this tool versus alternatives like 'intentfence_x402_assessment', nor does it provide conditions or exclusions.

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