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

Beyond the readOnlyHint annotation, the description discloses that the token scan covers a 'curated set' on EVM chains and that 'data comes back as it is'. It also adds input flexibility with ENS/SNS/aliases. This provides useful behavioral context, though it omits details like rate limits or response format.

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 front-loads the core purpose but then gets derailed by a truncated sentence ('maj —') and a long, tool-unspecific blurb about the MCP server, seat, and listing. It is not concise and contains substantial extraneous content.

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 lacks concrete parameter names, chain specification, output shape, and error behavior. The truncated token-set sentence creates ambiguity. Despite the read-only annotations, an agent cannot reliably construct a call without more detail.

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 defines no properties (additionalProperties only), so the description's statement that it 'Accepts ENS/SNS names and address-book aliases' adds meaningful guidance on what values to pass. However, it does not name the exact parameter keys or format, so it is not fully explicit.

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 returns 'Native and token balances for one address on one chain', which is a specific verb+resource. It also hints at a limitation (curated token set on EVM). However, it does not explicitly differentiate from sibling balance tools like orbitx_get_balance or singularityagent__portfolio, and the second half contains irrelevant server-level boilerplate.

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 single-address, single-chain balance queries and mentions acceptable input forms (ENS/SNS names, address-book aliases). It does not name alternatives or provide when-not-to-use criteria, and the 'read-shaped tools only' statement is generic to the whole server rather than tool-specific guidance.

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