ONCE

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

With no annotations, the description carries the burden of behavioral disclosure. It states the tool is 'safe' and that it demonstrates 'duplicate suppression', and instructs calling twice with the same id. However, it does not disclose what actually happens on duplicate calls (e.g., error, warning, or silent success), which is a minor gap for a demo tool.

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 consists of two concise sentences that are front-loaded and free of unnecessary detail. Every word earns its place, effectively conveying purpose and usage 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?

For a simple demo tool with one parameter and no output schema, the description is fairly complete. It states the safety, the behavior to demonstrate, and the exact invocation pattern. It does not describe return values or side effects, but given the demo context, the essential information for invocation is present.

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 only declares 'id' as a string with no additional description. The description compensates by explaining the role of 'id' ('same id'), clarifying that it is the key for duplicate suppression. This adds meaningful context beyond the raw schema, making the parameter's purpose understandable despite 0% 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 clearly states the tool's purpose: 'Safely demonstrate duplicate suppression.' This uses a specific verb ('demonstrate') and resource ('duplicate suppression'). It does not explicitly differentiate from sibling 'once_execute', but the title 'demo' and the context imply it is for demonstration, making the purpose 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?

The description provides explicit usage guidance: 'Call twice with the same id.' This tells the agent exactly how to invoke the tool to achieve its purpose. It lacks a direct comparison to 'once_execute', but the instruction is clear and contextually relevant, so it merits a 4.

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 burden of disclosure. It reveals key behavioral traits: stable idempotency key usage, post-state verification, and suppression of verified retries. This goes beyond a simple verb phrase, though it omits details about failure handling and return values.

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 sentences, front-loaded with the usage condition, and every clause contributes meaning. There is no redundant phrasing or over-specification.

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 (3 required params with nested objects, no output schema), the description provides a solid conceptual overview but lacks parameter-level detail, error/verification-failure behavior, and return value semantics. It is adequate for a high-level understanding but not fully complete for invoking the tool 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?

The schema coverage is 0% and the schema itself contains no parameter descriptions. The description only indirectly references 'idempotency key' and 'authoritative post-state,' mapping to idempotencyKey and verify, but it does not explain the structure of the 'action' object or provide guidance on parameter formatting. It fails to compensate for the missing schema 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 clearly states the tool's function: it executes an action with a stable idempotency key, verifies the authoritative post-state, and suppresses verified retries. This specific verb+resource combination distinguishes it from the sibling once_demo by emphasizing idempotency and verification.

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 explicitly opens with 'Use when retrying an external side effect could create a harmful duplicate,' providing a clear trigger condition. It does not explicitly mention when NOT to use it or alternatives like once_demo, but the usage context is unambiguous.

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