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

The annotations already declare readOnlyHint=true and openWorldHint=true. The description adds value by disclosing passthrough behavior: 'Called through their seat; their data comes back as it is' – indicating no post-processing or guarantees. It also reinforces the read-only nature with 'anything that buys, sells or writes refuses,' which aligns with annotations. No contradiction, and it adds context about the external service ('live seat on The Wall') without repeating annotation data.

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 main intent is front-loaded in the first sentence, listing the data points clearly. The second sentence adds context about the Orbitx server and read-only nature. The URL is an extra detail but not excessive. Overall, it's compact and focused, with no filler. Slightly loses a point for including the URL and extra 'This is their server' context that could have been omitted without losing core meaning.

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?

For a tool with 3 parameters, 1 required, and no output schema, the description is incomplete. It does not mention the required authCode parameter (though the schema does), nor does it explain the mint parameter's format or how to obtain authCode. The tool returns multiple data fields but no return structure is described. While the description lists the fields, it omits critical usage details like authentication prerequisites and parameter semantics, leaving an agent under-informed for correct invocation.

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 only 33% (only authCode has a description). The description does not explain mint (likely the token address) or chain (defaults to solana). It does not clarify how authCode is obtained or that it is required for Grok calls (though the schema notes it). With low schema coverage, the description was expected to compensate, but it provides zero parameter-level meaning, leaving agents to infer that 'mint' references a token identifier without explicit guidance.

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 verb ('get') and resource ('token') and lists specific data points: 'price, market cap, holders, OG score, trust verdict, forensics summary.' This is specific and distinguishes it from siblings like orbitx_get_chart or orbitx_get_balance by offering 'Full token intel,' implying a comprehensive view. The resource is unambiguous.

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 retrieving comprehensive token information but does not explicitly state when to prefer this over the many sibling tools (e.g., get_balance, get_chart). It mentions 'Read-shaped tools only' as a general constraint, but no explicit alternative or condition for when-not-to-use is provided. Usage context is inferred from the 'Full token intel' phrasing rather than directly stated.

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