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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds specific behavioral details: 'partial_upstream_response when upstream total>0 but list unparseable' and 'BTC items include inputs/outputs/tx_status'. It also includes disclaimers like 'No account access, no order placement or fund transfers' which reinforce the read-only nature but add little beyond annotations. Overall, it adds some edge-case context and per-chain behavior, but not deeply.

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 about 55 words and includes several short declarative sentences. It front-loads the core purpose and includes useful edge-case info. However, it contains somewhat lengthy disclaimers ('No account access... Not investment advice') that, while harmless, are not central to invoking the tool and could be trimmed. The structure is acceptable but not maximally efficient.

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 13 parameters and an output schema exists, the description need not detail return values. It covers a key edge case (partial_upstream_response), BTC specifics, and cross-references for chain aliases and profile usage. However, it does not clarify pagination mechanics (e.g., cursor vs. offset) beyond 'paginated', nor does it state explicitly what types of transactions are included (transfers only vs. all tx types). It is adequate but has noticeable gaps for a complex 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?

Schema description coverage is 100%, so parameters like chain, tx_type, time_range, and filters are already documented. The description adds 'Chain aliases same as get_address_info', which could clarify chain naming conventions, but the schema already lists examples and open-ended dots. No additional parameter semantics beyond the schema are provided, so the baseline of 3 is appropriate.

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 states 'Paginated transfers' as the core action, implying retrieval of address transactions. It also specifies BTC-specific data ('inputs/outputs/tx_status'), which adds nuance. However, it does not explicitly name 'transactions' beyond the tool name, and it omits mentioning that tx_type can be 'contract_call' or 'token_transfer', so the purpose is clear but not fully exhaustive.

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 provides a pointer to a sibling: 'Profile→get_address_info' suggests using get_address_info for profile queries, implicitly indicating this tool is for transactions. It also mentions 'Chain aliases same as get_address_info' for reuse. However, it does not explicitly state when to prefer this tool over other on-chain tools (e.g., get_transaction or get_token_onchain) nor give exclusions. The guidance is implied rather than explicit.

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