Proof Inbox

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 explicitly states the operation is read-only and 'Does not burn credits,' which are the key behavioral traits for a balance-checking tool. It stops short of detailing response behavior or error cases, but those are less critical here.

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 short sentences with no filler. Each sentence earns its place: what it does, when to use it, and the non-destructive side effect. The most important information is front-loaded.

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 optional, fully documented parameter, the description gives sufficient operational context: it is read-only, safe before a batch, and does not consume credits. The absence of an output schema means some return-value ambiguity exists, but the tool is simple enough that the purpose largely implies the response.

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 100%, so the schema already fully documents the single optional parameter. The description adds no parameter-level detail, but the baseline of 3 applies because the schema is doing the heavy lifting.

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 ('verify'), a clear resource ('credit balance'), and a scope ('for a workspace'). It explicitly labels the operation as read-only, which immediately distinguishes it from the sibling tools receipts and verify_email.

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 an explicit when-to-use instruction: 'Call this before a batch.' It does not mention alternatives or when not to use it, but the context is clear enough for a simple preflight balance check.

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?

With no annotations, the description carries the full burden and does well: it discloses 30-day cached free repeats, the payment_required/checkout_url behavior when credits are 0, the 'never invent results' reliability rule, and the meaning of 'unknown.' This goes well beyond a bare definition.

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 four short sentences with no filler. The core action is front-loaded, and each subsequent sentence provides a distinct and relevant behavioral detail.

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 two-parameter tool with no output schema, the description covers the main invocation and edge-case concerns: caching, credit exhaustion, unknown outcomes, and reliability expectations. It does not specify the success response format, but this is a minor gap given the tool's simplicity.

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 100% for both parameters, so the baseline applies. The description adds no parameter-specific meaning beyond what the schema already provides, although it does add broader billing and result 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 opens with 'Verify one email,' which states a specific verb and resource and distinguishes the tool from the sibling tools balance and receipts. The purpose is immediately clear without requiring schema inspection.

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 this is the tool for single-email verification, and it provides useful operational context such as caching and credit-exhaustion behavior. However, it does not explicitly discuss when to use this tool versus alternatives, though the siblings are unrelated in purpose.

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