system_info

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states this is a documentation-only tool with no API call and no credit consumption, which is a key behavioral trait. It also lists the detailed coverage of each action, giving a good sense of what the response will contain. While it doesn't describe response format or pagination, the tool is a simple reference lookup, so the disclosure is adequate.

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 effectively structured with a leading one-line summary followed by a bulleted list of actions. Each bullet is concise and informative, with no redundant or filler content. It packs a lot of useful detail into a compact format, making it easy to scan and understand.

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 tool has a simple interface with only one required parameter, and the description covers all possible enum values with detailed context. It also conveys the crucial fact that no credits are consumed, which is important for cost-aware agents. No output schema exists, but the description clearly indicates what type of information is returned for each action, making the tool fully understandable.

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 100% coverage with descriptions for both 'action' and 'context', so the baseline is 3. The tool description adds substantial meaning beyond the schema by detailing exactly what content each enum value provides (e.g., errors includes HTTP status, error code, message; callbacks includes retry strategy and HMAC). This goes above the schema's simple 'Reference topic to retrieve'.

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 'CryptoAPIs reference documentation — no API call, no credits consumed,' which precisely defines the tool as a documentation lookup rather than an operational API call. It then enumerates five distinct reference actions (blockchains, errors, credits, callbacks, limits), each accompanied by a brief scope. This clearly differentiates it from sibling fee-related tools like blockchain_fees_utxo/evm/xrp.

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 notes that no API call or credits are consumed, signaling that this tool is for retrieving reference information, not for executing transactions. Each bullet item specifies the kind of information retrievable, such as error tables, credit costs, and webhook mechanics, giving implicit when-to-use guidance. It does not explicitly mention alternatives, but sibling tools are fee-specific, so the usage context is clear.

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