ExitProof

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

With no annotations, the description carries the full burden. It discloses the payment requirement ($1.00) and the condition (after manifest access and actionability preflight succeed), and lists return components. However, it does not explain failure behavior, required permissions, or side effects beyond the payment. This is moderate 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 a single, front-loaded sentence that places the payment condition first and lists outputs efficiently. It is concise with no filler, though it packs a lot of information into one sentence, making it slightly dense.

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 lack of annotations and output schema, the description should provide more context. It lists outputs but does not explain the purpose of an exit pack, when to build one, what the preflight entails, or how it relates to the other tools. This leaves significant gaps for an agent to infer.

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, but it does not mention either parameter by name. It indirectly references 'manifest access' (implying manifest_id) and 'access' (implying access_token), but offers no explanation of their formats, roles, or how they are used. This leaves the agent with almost no parameter guidance beyond the schema patterns.

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 builds an exit pack and enumerates its components (cancellation/refund action plan, evidence checklist, suggested request, sources, limitations). It distinguishes from siblings by the verb 'build' and the resource 'exit pack', though it does not explicitly contrast with other tools. The purpose is specific and understandable.

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 no guidance on when to use this tool versus its siblings (check_reversibility, create_exit_manifest, etc.). It mentions a preflight condition but does not explain the decision context or prerequisites beyond that. No alternatives or exclusions are 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?

With no annotations, the description carries the full burden of behavioral disclosure. It usefully states cost behavior ('Free', 'Never charges') and implies a read-only evaluation, but it does not disclose side effects, data handling, or response characteristics.

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?

Extremely short and front-loaded, with no filler. However, 'Free' and 'Never charges' are redundant, which costs a point.

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 11 parameters, 3 required fields, nested objects, no output schema, and four sibling tools, the description leaves the agent without usage details, return information, or differentiation. It is not complete enough for reliable 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 18%, and the description offers no guidance for the required parameters merchant, commitment_type, and amount, nor for the nested checkout_terms object. It only vaguely gestures at 'transaction-specific checkout terms' without adding meaningful parameter semantics.

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?

States a clear evaluative action on checkout terms and policy evidence. The verb 'Evaluate' plus resource identifies what the tool does, though it does not explicitly contrast it with sibling tools like list_supported_policies.

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 phrase 'before a real-world commitment' gives clear context for when to invoke the tool. It does not name alternatives or exclusions, which keeps it from a 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?

With no annotations, the description carries full behavioral burden and does well by disclosing the $0.25 fee, the preflight gating condition, privacy-minimization, durable storage, and one-time access token return. It omits side effects like overwrites or auth requirements, but the disclosed behaviors are significant and useful.

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 at two sentences with no filler. The cost/preflight condition is front-loaded, though placing the core action ('Stores a privacy-minimized durable record...') in the second sentence slightly delays primary purpose identification.

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 11-parameter schema, nested object, and absence of an output schema, the description is too high-level. It does not explain how the one-time token is used, what 'exit terms' encompasses, error behavior, or fee edge cases, leaving an agent with significant gaps for reliable 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 18%, and the description adds no parameter-level meaning. Required fields like merchant, commitment_type, and amount are not elaborated, and the nested checkout_terms object is left entirely unexplained, so the description does not compensate 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 identifies the core action ('Stores a privacy-minimized durable record of the exit terms') and the return value (one-time access token), making clear this tool creates an exit manifest. It does not explicitly differentiate from siblings like get_exit_manifest, which keeps it from a 5, but the purpose is understandable on its own.

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 a key prerequisite: use only after reversibility evidence passes preflight, which implies sequencing after check_reversibility. However, it provides no explicit when/when-not guidance relative to sibling tools like build_exit_pack or get_exit_manifest.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does add useful traits: 'Free' (cost), 'unguessable manifest ID' (security), and 'retrieve' (read-only implication), which the schema does not convey. But it does not mention failure modes, rate limits, or what the response contains, so transparency is only partially addressed.

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 only two sentences and gets to the core action immediately. The leading 'Free.' is an extra fact but is a single word and does not bloat the definition. Overall, every sentence earns its place, with only minor potential trimming.

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?

This is a simple read tool with two required parameters, but the description omits what a successful response looks like or how errors are signaled (e.g., invalid ID/token). With no output schema or annotations, an agent is left to infer the return value, making it adequate but not fully complete for smooth 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 0%, so the description must compensate for parameter meaning. It does label manifest_id as 'unguessable' and access_token as an auth token, giving some semantic role beyond the raw property names. However, it does not explain how they relate to each other or what the access token authorizes, so the added value is limited but not absent.

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 the specific verb 'Retrieve' and names the resource 'Exit Manifest', and the qualifier 'previously created' clearly distinguishes this from sibling tools like create_exit_manifest and list_supported_policies. An agent can immediately tell this is a get-one-by-id operation, not a creation or listing tool.

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 phrase 'previously created' implies the tool is for fetching an existing manifest, which gives context that creation must have happened first. However, it does not explicitly name alternatives or state when not to use this tool, leaving the when-to-use guidance implicit rather than 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?

With no annotations provided, the description carries the full burden and adds meaningful behavioral context: the list is of 'maintained' overlays, and absence from the list does not prevent checking a merchant if transaction-specific checkout terms are supplied. It does not detail output format or pagination, but the disclosed fallback behavior is a genuinely non-obvious trait.

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 short sentences with the core purpose front-loaded in the first sentence and the key caveat in the second. The 'Free.' note is minimal and the rest of the text contains 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 zero-parameter list tool with no output schema and no annotations, the description gives the essential return concept—maintained merchant policy overlays—and an important edge case about checking merchants not in the list. It could mention response shape, but the low complexity makes this description nearly 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 input schema declares zero parameters, so there is no parameter documentation needed and the schema fully covers the empty parameter set. The description therefore does not need to add parameter-level meaning.

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 states a specific verb and resource: 'List maintained merchant policy overlays,' which clarifies what 'supported policies' in the title refers to. This clearly differentiates the tool from sibling actions like build, check, create, and get.

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 the tool—when you need the maintained list of merchant policy overlays—but does not explicitly name alternatives or state when-not-to-use it. The fallback note about transaction-specific checkout terms offers useful context but leaves the alternative path unnamed.

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