arc_touchstone

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

With no annotations, the description carries the behavioral disclosure burden. It explains the nature of an assay (a reverted buy-and-sell), the contract address, and the fee's destination when creating one. However, it does not disclose the tool's own behavior (e.g., whether it is read-only, pagination, error cases, or output format). The description focuses on the assay concept rather than the tool's execution.

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 informative but slightly dense. It defines the assay concept, provides a contract address, and explains how to create an assay—information that may be tangential for a read tool. However, every sentence adds context, and it is not overly verbose. The core read functionality is stated early, and the later details are supplementary.

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 does not explicitly state the return format. It implies the read returns verdict, round-trip cost, and streak from the assay definition, but it does not confirm the output schema or any potential pagination. Given the tool takes an optional token and has no output schema, the description should clarify what the caller receives. The instruction about creating an assay via contract call is additional context but not directly relevant to the tool's interface.

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 describes the single parameter as 'Optional token address to read assays for.' The description adds meaningful distinction: if a token is provided, you read that token's assay; if omitted, you read all pools. This clarifies the parameter's behavior beyond the schema and directly maps to the two use cases.

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: 'Read every pool's last assay and streak, or one token's.' This is a specific verb (read) and resource (assays), and it also defines what an assay is. While it doesn't explicitly name a sibling tool, the unique concept of 'on-chain assays' distinguishes it from the other Arc-related tools like arc_exit_check or arc_pools.

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 says when to use the tool ('Read every pool's... or one token's') but does not provide explicit exclusions or name alternatives. It indirectly suggests that creating an assay is done via a direct contract call ('To make one, call assay(poolKey, 0)...'), implying this tool is for reading, but it never compares to other tools or states when not to use it.

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