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

The description claims 'Read' behavior, yet annotations have readOnlyHint=false, creating a contradiction (flagged). It adds that the call is public and requires no auth, which is useful, but the generic execution guidance adds noise. With the contradiction, the transparency is undermined.

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 tool-specific part is only 12 words, but it is followed by lengthy, generic execution guidance that repeats across tools. This boilerplate reduces conciseness and front-loads irrelevant details. A more focused description would be better.

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 simplicity (read balance) and that an output schema exists, the description could be more complete. It lacks details about error cases, rate limits, or cluster usage. The contradiction with annotations further reduces completeness.

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 coverage is 100%, so parameters are well-described in the schema. The description adds minimal context beyond 'base-chain SPL token balance', which is not parameter-specific but provides overall context. Baseline 3 is appropriate as the description does not significantly augment parameter meaning.

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 'Read the base-chain SPL token balance for an address', specifying the verb 'Read' and the resource 'SPL token balance'. It also notes it is 'public, no auth required', which distinguishes it from potential private alternatives. However, it does not explicitly differentiate from the sibling 'magicblock_privateBalance', which could be clearer.

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 mentions 'public, no auth required' and includes execution guidelines about free calling and routing, but does not explicitly state when to use this tool versus alternatives like magicblock_privateBalance or when not to use it. The guidance is more about execution context than usage decisions.

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