Trace

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful behavioral context by mentioning the stage timeline and the normalized representation, but it does not disclose error behavior, response structure, or any rate-limit concerns. This is adequate but not rich.

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 extremely concise, uses three short sentences, and front-loads the core action before the reference to the sibling representation. Every sentence contributes useful information 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 one-parameter read operation with strong annotations and full schema coverage, the description is largely complete. It tells the agent what will be returned (stage timeline and normalized representation), though it omits failure or not-found behavior. Given the tool's simplicity, this is a minor gap.

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 fully documents the single parameter, including a concrete example ('tr_abc123'). The description reinforces the trace_id format but does not add meaningful meaning beyond the schema, so the baseline 3 applies.

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 action ('Retrieve'), the resource ('an existing Trace payment trace'), and the lookup key ('trace_id'). It also differentiates the tool from its siblings by noting it returns the stage timeline and the same normalized representation as trace_payment.

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 usage context is implied: use this tool to fetch an existing trace by trace_id, and because it is read-only it is appropriate for inspection. However, it never explicitly names when to prefer this over trace_payment or states an exclusion condition, so the guidance is 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, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds useful behavioral context by disclosing explicit capability flags (read-only; cannot send, retry, or sign) and clarifying that providers require connected credentials, which goes beyond the structured fields.

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 dense sentence that front-loads the purpose and then packs the output categories into a parenthetical list, followed by a helpful use cue. It is efficient, though the long first sentence is somewhat overloaded with details.

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 no parameters, an output schema, or nested objects, the description is complete: it enumerates the categories of information the tool provides (assets, chains, providers, capability flags) and gives a clear decision rule for when to invoke it. An agent has enough context to call and interpret the result without additional documentation.

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 trivially 100%, so there is no parameter meaning for the description to add. With no parameters, a baseline of 4 is appropriate, and the description instead invests its space in explaining the result content.

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 names a specific action ('List'), the resource ('what Trace supports and can do'), and enumerates concrete categories: assets, chains, providers, and capability flags. It also implicitly distinguishes itself from trace_payment by framing itself as the scope-checking entry point, so an agent can tell it apart from siblings.

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 to call this tool 'when unsure whether a payment is in scope for trace_payment,' which is a clear usage trigger and names a sibling alternative. However, it does not give an explicit when-not-to-use statement or contrast with get_trace, so it stops just short of full alternative routing.

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 (readOnly, idempotent, openWorld, non-destructive), the description discloses meaningful behaviors: it never moves funds or retries payments, public blockchain data needs no auth while provider state requires an API key, and it explicitly warns that onchain finality does not prove beneficiary bank credit and 'unknown never means failed.' This is exactly the kind of contextual behavior annotations alone do not convey.

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 longer than average, but every sentence earns its place: purpose, triggers, input formats, output semantics, auth requirements, and safety guardrails. It is front-loaded with the core use case and uses plain, direct language. Though verbose, there is no fluff.

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?

Despite having no output schema, the description summarizes the return value (normalized state, flags, health, diagnosis code, suggested action, retry timing, and knowledge model) so an agent knows what to expect. It also covers authentication, input requirements, and post-call safety behavior, making it complete for the tool's complexity.

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 fully describes both parameters (100% coverage), but the description adds domain-specific meaning by enumerating supported identifier forms (Base transaction hash, Solana signature, Bridge transfer ID, Circle payment ID, wallet address) and instructs the agent to ask the user for an identifier if none is provided. This adds behavior around the input parameter beyond the schema's generic description.

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 a precise statement of what the tool does: determining whether a stablecoin payment completed, failed, or is delayed, including where the money is and who owns the next step. Typical triggers like 'the recipient says the payment never arrived' make the purpose unmistakable. It does not explicitly contrast with sibling tools get_trace or list_supported_systems, so an agent must infer differentiation from the detailed output description.

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 explicitly states when to use the tool ('Use this whenever you need to determine...') and gives typical user trigger phrases. It also provides a clear exclusion: do not use it to send or swap anything, and if a payment is unresolved, do not send a replacement. However, it never names alternative sibling tools or conditions for choosing them, so it stops short of a full 5.

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