GAIP Buyer Assurance Agent

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

Annotations indicate readOnlyHint=false, destructiveHint=false, and openWorldHint=true. The description adds that the tool checks a response/replay and verifies a receipt, implying a verification/validation operation. It does not disclose side effects, permissions, or failure behavior, but the annotations already cover the safety profile. The description adds moderate context beyond 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 a single sentence that is concise and front-loaded with the main action. It earns its place by stating the core purpose without fluff, though it could be slightly more structured by separating the two checks.

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 7 parameters, 0% schema coverage, no output schema, and no explicit usage guidance, the description is incomplete. It does not explain the meaning of key parameters like data_classification, body_sha256, http_status, or content_type, nor does it describe the return value or how the verification result is presented. An agent would struggle to invoke this tool correctly with only the description.

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 the 7 parameters. It mentions 'buyer-submitted public response or later public replay' and 'registered terms' and 'retained receipt', which loosely maps to mode, terms_id, and body, but it does not explain data_classification, body_sha256, http_status, or content_type. The description provides only partial semantic guidance for the parameters.

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 ('Check') and resource ('a buyer-submitted public response or later public replay against registered terms and verify the retained receipt'). It clearly identifies the tool's function and distinguishes it from siblings like assurance_prepare and assurance_verify, though it doesn't explicitly name them.

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: when a buyer-submitted public response or later public replay needs to be checked against registered terms and the retained receipt verified. However, it does not explicitly state when not to use it or name alternative tools, leaving some inference to the agent.

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=false and destructiveHint=false, meaning the tool may write but is not destructive. The description says 'record', which aligns with a write operation, and adds that it does not involve supplier appointment, call, contract, or payment. This adds some behavioral context beyond annotations, but it does not disclose side effects, persistence, or any further consequences of recording. No contradiction is present.

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, tightly worded sentence that front-loads the primary action and scope. Every word earns its place, and the negation is concise. There is no redundancy or 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 the tool's complexity (7 parameters, 0% schema coverage, no output schema), the description is far too sparse. It does not explain prerequisites, expected outcomes, return values, or parameter meaning. An agent cannot reliably construct a valid call based solely on this description and the schema. The description lacks essential context for correct 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 carries the full burden of explaining parameters. The description mentions 'public service' and 'checks', but does not explain any of the 7 parameters (data_classification, counterparty_id, service_url, task_class, checks, episode_id, explicit_read_only_consent). It provides no mapping from natural language to fields, leaving the agent to infer meaning from names alone. This is a significant gap for a tool with 7 parameters.

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 ('Preflight') and resource ('one buyer-selected public service'), and clearly indicates the action is to 'record caller-declared delivery checks'. It explicitly negates what it does not do (no appointment, call, contract, payment), which distinguishes it from siblings like assurance_complete and assurance_verify that likely handle subsequent steps. This is precise and unambiguous.

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 context that this is a preparatory step and explicitly excludes certain actions, but it does not name alternative tools or state conditions for when to use this vs. others. It implies usage as a preflight check but does not give explicit 'when to use' or 'when not to use' guidance beyond the negation. This is adequate but not fully 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only safety profile is covered. The description adds one meaningful behavioral detail—that no external-use credit is assigned—but does not disclose other traits like what 'retained' means, authentication needs, or what happens on failure.

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 with no filler. It states the action, the target resource, and the key constraint ('without assigning external-use credit') efficiently, making it easy for an agent to parse quickly.

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 one-parameter verification tool with read-only annotations, the description is mostly adequate. However, with no output schema, it does not describe what the agent should expect as a return value, and it leaves the distinction from verify_gaip_receipt implicit rather than explicit.

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 the undocumented receipt_id parameter. It only implies that receipt_id refers to the terms or delivery receipt being verified, but it does not explain the expected format, where the ID comes from, or any constraints. This is minimal compensation for a single required parameter.

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 ('Verify') and names a concrete resource ('retained Buyer Assurance terms or delivery receipt'), and adds a scope qualifier ('without assigning external-use credit'). It is clear enough to distinguish from most siblings by domain, though the 'or' phrasing is slightly ambiguous and it does not explicitly contrast with similar tools like verify_gaip_receipt.

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 verifying retained Buyer Assurance terms or delivery receipts without assigning external-use credit. However, it provides no explicit guidance on when not to use it or which sibling alternative to choose, such as verify_gaip_receipt or witness_delivery.

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