Proof Inbox

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

With no annotations, the description carries full behavioral burden and handles it well: declares read-only, states cost is 0, and describes the payment_required response branch including token persistence and checkout_url handling.

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?

Every sentence earns its place: purpose, call sequence, conditional handling, cost, and auth. The description is compact yet information-dense without 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?

Complete for a tool with no annotations and no output schema: it explains when to call it, what to do after, how to handle the unpaid case, and the auth transformation. An agent has enough guidance to invoke it correctly.

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 the schema already documents the parameter well. The description adds further meaning by explaining how workspace_token is used in the payment flow as Authorization: Bearer.

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 specific verb and resource: 'Read-only verify credit balance.' This clearly differentiates from siblings like verify_email and buy_credits by naming the exact operation and its read-only nature.

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 explicit orchestration guidance: call this, then call verify_email, do not stop at tools/list, and retry with persisted workspace_token on payment_required. It also names the conditional branch for unpaid balances.

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 discloses the SKU options and default, the required token persistence, the human-operation step, and the post-payment retry behavior. It also adds a caution ('Do not invent a URL') that helps constrain agent 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?

The description is compact and front-loaded, stating the core purpose first, then layering essential operational details. Every sentence contributes useful information: the SKU options, the auth-header behavior, the human-in-the-loop step, and the post-payment retry. There is 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?

The tool has no output schema, so the description needs to convey what the agent should do with the response. It does mention opening checkout_url, which implies the response provides a URL, but it does not explicitly describe the response shape or mention potential failure/error handling. Overall it is nearly complete for a simple two-parameter purchase 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?

Schema coverage is 100%, so the schema already documents both parameters. The description adds value beyond the schema by specifying the concrete SKU values, their prices, and the default (verify_500). This gives the agent actionable selection information that the schema alone does not provide.

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 and object: 'Create a checkout session for verify credits.' This clearly identifies the resource being acted on and the action taken, and it is unambiguously distinct from the sibling tools (balance, receipts, verify_email). The tool's purpose is fully self-contained.

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 clear usage context by walking through the full workflow: create the session, pass the workspace token, open checkout_url for the human, and retry verify_email after payment. It does not explicitly state when not to use this tool versus alternatives, but the workflow context makes the intended use obvious.

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 behavioral burden. It discloses that the tool lists workspace-scoped proof of spend/checks and warns against fabricating checkout session IDs, but it does not state auth requirements, side effects, or return-shape behavior beyond the implication of 'List'.

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 the action and resource, followed by a clear trigger condition and a concise anti-hallucination warning. 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?

The definition gives a clear purpose and use case, and the schema covers limit bounds and token auth, but with no output schema and an undocumented receipt_id parameter, the agent must infer some invocation details. It is adequate but not 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 coverage is only 33% because only workspace_token has a description. The description mentions checkout session IDs but does not explain limit, receipt_id, or how the workspace token vs. Bearer auth should be handled, so it 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 uses a specific verb ('List') and names a distinct resource ('proof of spend and proof of checks for this workspace'), which helps an agent tell it apart from balance and verify_email. It could be stronger by explicitly contrasting with sibling tools, but the resource and action are clear.

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?

'Use this when the human asks what a charge paid for' gives an explicit trigger condition for when to select the tool. It lacks a when-not-to-use statement or alternatives, but the practical warning 'Do not invent checkout session ids' adds useful 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?

No annotations are provided, so the description carries the full disclosure burden. It covers caching behavior, cost, the payment_required path, retry after checkout, and the unknown result semantics, and cautions the agent not to fabricate results. This is rich non-obvious behavioral information beyond the schema.

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 dense and front-loaded, with each sentence carrying useful information: action, cost/caching, payment recovery, and result semantics. No filler or repetition of schema fields.

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 and no annotations, the description covers the main non-obvious scenarios (cached, paid, unpaid, incomplete) well enough to guide invocation and follow-up. It does not enumerate every success result value, but it provides the critical unknown and payment_required cases and warns against inventing results.

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 the schema already describes both parameters. The description adds meaningful behavior for workspace_token by telling the agent to persist it as Authorization: Bearer and retry after payment, which is not present in 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 explicitly states the core action 'Verify one email now' with a clear verb and resource. It also distinguishes itself from listing operations with '(listing tools is not a verify)', helping an agent avoid category confusion.

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 concrete usage context: cached repeats are free, fresh checks cost 1, and it explains the payment flow with checkout_url and token persistence. It does not name sibling tools like balance or buy_credits as alternatives, but it clearly indicates this is the tool for a single verification and excludes listing-type operations.

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