Tatum MCP Server

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it's a read operation (implied by 'Get balances'), discloses the cost ('50 credits per API call'), mentions deprecation status and timeline, lists supported blockchains, explains response content (balances with metadata unless excluded), and notes parameter limitations (e.g., 'Following query parameters won't have any effect on filtering data excludeMetadata'). However, it doesn't cover rate limits, authentication needs, or error handling.

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 overly verbose and poorly structured. It mixes deprecation warnings, usage notes, parameter explanations, and blockchain lists in a dense paragraph. Key information (like the deprecation) is buried, and sentences like 'Following query parameters won't have any effect on filtering data excludeMetadata' are confusing. It could be significantly streamlined for better readability.

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 (6 parameters, no output schema, no annotations), the description does a reasonably complete job. It covers the purpose, deprecation context, supported blockchains, basic usage, response content, and some parameter behaviors. However, it lacks details on output format (e.g., what the balance data looks like), pagination behavior (though offset and pageSize are in schema), and error cases, which would be helpful for an agent.

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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds some context by mentioning 'comma-separated list of addresses' (redundant with schema), 'excludeMetadata to true' (redundant), and token type filtering options (partially redundant with schema's enum description). It provides minimal additional semantic value beyond what's in the schema, meeting the baseline for high coverage.

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 purpose: 'Get balances of native, fungible tokens (ERC-20), NFTs (ERC-721 and ERC-1155) or multitokens (ERC-1155 only) for a specific wallet address on the following blockchains...' It specifies the exact resource (wallet balances), the types of tokens included, and distinguishes it from the newer sibling tool 'get_wallet_portfolio_v4' by explicitly mentioning the deprecation and recommending migration.

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 explicit guidance on when to use this tool versus alternatives: it states that the endpoint is deprecated, recommends migrating to 'GET /v4/data/wallet/portfolio' (which corresponds to sibling tool 'get_wallet_portfolio_v4'), and gives an end-of-life date. It also explains when to use it ('To get started: Provide a chain name and comma-separated list of addresses') and mentions limitations like the Tezos-specific behavior.

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