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

The description states 'Read-shaped tools only (anything that buys, sells or writes refuses)', implying the tool is read-only. However, the annotations explicitly set readOnlyHint=false, directly contradicting this claim. This is a serious inconsistency that undermines the agent's ability to predict side effects. The description also adds extraneous context about the server and a truncated 'w' without clarifying behavioral details.

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 verbose and includes irrelevant server metadata ('Singularity Agent's MCP server, a live seat on The Wall', a listing URL) that does not help the agent invoke the tool. It also appears truncated ('w —'), likely an artifact. While the core purpose is front-loaded, the excess verbiage detracts from its clarity and does not earn its place.

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 is incomplete for an agent to confidently call the tool correctly. It lacks any mention of expected input (if any), return format, or error behavior. The contradiction between the read-only claim and readOnlyHint false creates ambiguity. With no output schema, the description should at least explain what the response contains; it partially does (permissions) but omits crucial details like how the mint is identified or what fields are returned. The extraneous server context further muddles 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?

The tool has zero parameters in the schema, and schema_description_coverage is 100%. Per the calibration rule, 0 parameters yields a baseline of 4. The description does not add specific parameter guidance, but none is needed for a parameterless call; the open schema (additionalProperties: true) suggests the agent may pass arbitrary properties, though the description does not clarify expected inputs like a mint address. Nevertheless, with zero defined parameters, this is acceptable.

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 reads a Solana mint account's permitted operations, enumerating specific aspects: token program owner, mintability, and freeze authority. The verb 'read' and resource 'Solana mint account' are present, making the core purpose apparent. However, it does not explicitly distinguish itself from sibling tools like singularityagent__token_identity or singularityagent__read_contract, so it falls short of full differentiation.

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 offers no explicit guidance on when to use this tool versus alternatives. The phrase 'Read-shaped tools only' is a general constraint of the MCP server, not a usage guideline for this specific tool. There is no mention of preferred contexts, prerequisites, or exclusions relative to sibling tools.

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