system_info

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

With no annotations, the description must disclose behavioral traits. It explicitly states 'no API call, no credits consumed', indicating a read-only, side-effect-free operation. It also details what each action returns (e.g., 'credit charging structure', 'webhook mechanics'), giving insight into behavior. However, it does not explicitly mention idempotency, authentication requirements, or error behavior, but these are less relevant for a reference 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 well-structured and appropriately sized. It front-loads the core purpose in the first sentence, then uses bullet points to list actions efficiently. Every sentence adds value, and the format improves scannability. There is no redundancy or unnecessary 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?

Given the tool's complexity (2 params, no output schema), the description is highly complete: it enumerates all five actions and describes the content of each. It covers the 'context' parameter's behavior indirectly by mentioning it only in the schema. While it does not specify response format or error handling, for a reference documentation tool this is sufficient and the description fully supports agent usage.

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 covers both parameters (action, context) at 100%, so baseline is 3. The description adds significant meaning by explaining what each enum value of 'action' provides, e.g., 'blockchains — Supported blockchains, networks, products per chain, denominations, fiat currencies'. This goes beyond the schema's simple 'Reference topic to retrieve' and provides richer semantic 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 provides CryptoAPIs reference documentation with no API call or credits consumed, and lists five specific actions (blockchains, errors, credits, callbacks, limits). This distinguishes it from sibling tools like manage_address or history tools, which are operational. The verb 'retrieve' is implied and the resource (reference topics) is explicit.

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 usage for obtaining reference information, emphasizing 'no API call, no credits consumed' which positions it as a safe exploratory tool. It does not explicitly name alternatives or state when not to use it, but the context is clear given its reference nature and the sibling tools are operational. The listing of actions provides a direct way to decide which action to invoke.

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