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

With no annotations, the description explicitly discloses that the tool has no side effects ('pure function') and will not fetch URLs or run code. This is strong transparency, though it does not mention whether any state changes occur or what happens on invalid input.

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 compact and packed with useful information, though the opening sentence is cryptic and the list format is somewhat dense. Overall, it communicates key points without unnecessary padding.

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 explains inputs and behavior but lacks an output schema or any mention of return values, error handling, or success criteria. It also does not clarify how this tool differs from receipt_verify or other siblings, leaving some context incomplete.

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 description explains the meaning of 'check' by enumerating allowed values and describes 'input' as the data being checked. It also notes that ed25519 requires 'signature' and 'public_key', giving conditional semantics beyond the bare schema. However, optionality and mutual exclusivity are not fully specified.

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 lists the specific check types (json, sha256, base64, receipt, ed25519, costas, permutation) and what each validates, making the tool's purpose clear. However, phrases like 'Ground truth: a check you cannot run on yourself' are ambiguous and the relationship to sibling tools like receipt_verify is not clarified.

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 states that the tool is a pure function and will not fetch URLs or run code, which gives some safety guidance. It does not explicitly explain when to prefer this tool over siblings such as receipt_verify or question_answer, leaving selection criteria partly implicit.

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