ONCE — Exactly-Once Reliability for AI Agent Actions

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

With no annotations provided, the description fully carries the behavioral disclosure. It transparently states that the tool is a safe, zero-setup demo with no external side effects, and that calling it twice with the same id will suppress the second execution. This precisely describes the observable 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 two sentences with no filler. The first sentence immediately labels it a 'SAFE ZERO-SETUP DEMO' and states the action; the second sentence provides usage context. Every word earns its place and the key 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?

Given the low complexity (1 parameter, no output schema, no annotations), the description is complete. It covers what the tool does, safety aspects, how to use it (twice with same id), and the expected outcome. There is no critical missing information for a demo 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?

The input schema already provides a clear description for the 'id' parameter, covering the reuse requirement. Coverage is 100%, so the baseline of 3 applies. The tool description adds no additional parameter semantics beyond restating the same-id usage, which the schema already conveys.

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: it is a safe demo to demonstrate ONCE duplicate suppression by calling it twice with the same id. The verb 'Call' and resource 'ONCE' are specific, and it distinguishes itself from the sibling tool once_execute by being a zero-setup, no-side-effect demo.

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 says 'Use this when evaluating or discovering ONCE' and notes that no API key or external side effect is required. This gives clear context for when to use it, though it does not explicitly name once_execute as the alternative for real execution. The guidance is clear but could be more explicit about when not to use this tool.

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. It discloses that it uses a stable idempotency key, executes the action, verifies authoritative post-state, and suppresses verified retries. However, it omits failure handling, error conditions, and the irreversibility of side effects, which are important for a consequential 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 is two concise sentences, front-loaded with the triggering condition and listing use cases. No wasted words; every part earns its place.

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 complex tool with nested objects and no output schema, the description lacks return value expectations and failure behavior. It doesn't explain what the agent should expect after calling, leaving some critical context missing for safe execution.

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%, with only idempotencyKey having a description. The description repeats the idempotency key concept but adds no meaning to action or verify structures beyond what the schema already shows, failing to compensate for the low 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 with a specific verb ('prevent duplicate consequential actions') and lists concrete scenarios (purchase, refund, payment, etc.). It also explains the mechanism (idempotency, verification, suppression), which distinguishes it from the sibling once_demo as the real execution tool.

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?

'CALL THIS when an AI agent is about to perform or retry a consequential external side effect' explicitly indicates when to use. It gives a clear set of use cases, though it doesn't discuss alternatives or when not to use, so a small gap remains.

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