Gateway Agent Tip Jar

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description adds value beyond those: it discloses the requirement for the original Authorization header and clarifies that 'pending/error is not confirmation,' which is critical behavioral context. It is consistent with annotations and adds useful nuance, so 4.

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 concise sentences with no redundancy. The core purpose is front-loaded, and the caveat about confirmation is included without bloat. Every sentence earns its place, so 5.

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 read tool with two parameters and no output schema, the description covers purpose, a key parameter, and an important caveat about confirmation. It lacks explicit details on jobId semantics, but the pattern and name are self-explanatory, and annotations cover safety. It is sufficiently complete for an agent to call it correctly, so 4.

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 explains includeResult (requests the result) and hints at auth for jobId, but does not describe jobId itself beyond its name and pattern. It adds meaning for one of two parameters, so 3.

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 ('Read') and resource ('existing private job status or finalized contribution receipt'), and clarifies it never creates or retries a payment. This clearly distinguishes it from a creation tool, though it does not explicitly name the sibling prepare_tip_quote. It is clear but lacks explicit sibling naming, so 4.

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 context on when to use (reading status/receipt) and explicitly states what it does not do (never creates/retries), which indirectly guides away from other tools. However, it does not name alternatives or specify conditions for using get_tip_terms instead. It provides some guidance but no explicit exclusions, so 3.

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, openWorldHint, idempotentHint, and destructiveHint false. The description adds meaningful context beyond those by explicitly stating 'Discovery never authorizes spending' and 'No wallet or account required,' which reassures agents about side effects and prerequisites.

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 short sentences with no filler. The core action is front-loaded, and each additional sentence adds distinct value: one addresses authorization safety, the other addresses access prerequisites.

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 parameterless read-only tool with strong annotations, the description fully covers what an agent needs to know: it is a safe, free, account-less discovery operation. No output schema exists, but the simple nature of the tool does not demand more.

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 tool has zero parameters and the schema coverage is 100%, so there is no parameter meaning for the description to add. Per the baseline for zero-parameter tools, this is effectively complete.

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 'Read free optional tip terms,' a specific verb plus resource that clearly identifies the tool as a read-only lookup. It is easily distinguished from siblings like prepare_tip_quote and get_tip_receipt, which imply quote preparation and receipt retrieval.

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 clear context: this is for discovery only, never authorizes spending, and requires no wallet or account. It does not explicitly name sibling tools or say when not to use it, but the behavioral caveat effectively separates it from spending-related operations.

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?

Beyond the annotations, the description discloses critical behavior: the quote is UNPAID, the tool 'never signs or pays,' it requires a locally generated private capability, and both the quote and idempotency key must be persisted first. This adds real behavioral context that annotations alone do not provide. No contradiction with the 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?

Three short sentences, each earning its place. The main purpose is front-loaded, and the constraints and non-behavior are stated without unnecessary wording.

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 prerequisites, auth, persistence, and the critical exclusion of signing/paying. It is not perfect only because there is no output schema and the description does not describe the return value, and the pronoun 'it' in 'Persist it' is slightly ambiguous.

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 schema documents amount and maxAmountUSD as USDC decimal strings, but the description adds meaning by mapping maxAmountUSD to 'budget' and ownerAuthorized to 'owner permission.' It also stresses the idempotencyKey's role by saying to persist it first. This meaningfully compensates for the 50% schema description 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 states a specific action and resource: 'Reserve an UNPAID optional tip quote.' This clearly differentiates it from the read-only sibling tools get_tip_receipt and get_tip_terms, since this tool creates/reserves rather than retrieves.

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?

It gives clear conditions for use: 'only with owner permission and budget,' requires a private capability in the Authorization header, and tells the agent to persist the idempotency key first. It does not explicitly name alternatives or say when not to use it, but the constraints are strong and actionable.

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