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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, indicating safe, non-mutating behavior. The description adds useful context: it's cache-only, open to everyone, and that unknown fields are null rather than guessed. It also warns about the meaning of have_record=false, which is beyond the annotations. However, it doesn't elaborate on response structure or potential rate limits, but the annotations cover the safety profile.

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 two sentences, highly concise, and front-loads the core purpose and key behaviors. Every sentence adds value: the first details what facts are checked, the second clarifies open/cache-only and introduces the have_record warning. No fluff or redundant information.

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 moderate complexity (one parameter, no output schema), the description is largely complete. It covers what the tool checks, the safety profile (via annotations), and the cache-only behavior. The only minor gap is the absence of explicit return value description, but since there's no output schema, a brief note on response format could be beneficial. However, the 'Facts, not advice' line and the have_record clarification add necessary context.

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 has one parameter (address) with 0% description coverage, so the schema provides no semantics. The description doesn't explicitly mention the 'address' parameter, but it's implied by 'token' context and the tool's purpose. It doesn't explain the format of the address (e.g., Solana vs Ethereum) or provide additional meaning beyond 'the token address.' Since there's only one parameter, the description partially compensates, but a bit more specificity would help.

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 what the tool does: checks if a token can be sold and what the deployer can still do (mint/freeze authority, dev share, liquidity position). It uses a specific verb ('check') and resource ('token'), and the title reinforces the purpose. It could be slightly more explicit about the 'exit_check' name, but overall it distinguishes itself from other tools by focusing on exit/liquidity and dev control.

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—'Open to everyone, cache-only'—and sets expectations for when to use it, but it doesn't explicitly state when NOT to use it or name alternative tools. It mentions 'have_record=false means no read, not safe,' which is a form of guidance but somewhat cryptic. It could benefit from clarifying that this is for token safety checks versus general token info (like sol_token_detail).

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