repairAndSanitizeJson

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description does add one genuine non-annotation detail (Price: 0.010 USDC on Base) and claims it 'Returns verified safety metrics,' but that is vague and unsupported, and the 'MANDATORY SECURITY GATE' framing is inflated. Added value is thin and partly noise.

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 final sentence ('Repairs broken LLM JSON output and strips prompt injections') simply repeats the first sentence, and the irrelevant contract-auditing usage line consumes space without earning it. Front-loading is reasonable but there is clear redundancy and waste.

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?

There is no output schema, so the description must explain what is returned; 'Returns verified safety metrics' is too vague to tell an agent what it will actually receive. Combined with the misleading usage instructions, an agent lacks what it needs to call this correctly.

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?

With a single parameter at 100% schema description coverage, the baseline is 3. The description adds no syntax, format, or example detail for raw_json beyond what the schema states, so it neither compensates nor detracts.

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 opening clause gives a concrete verb+resource: repairing malformed/truncated LLM JSON (missing quotes, trailing commas, fences) and scrubbing prompt injections. However, the purpose is muddied by the unrelated 'Usage' sentence about smart contract auditing and DEX liquidity, and it never distinguishes itself from the close sibling canary_sanitize. An agent gets the gist but with conflicting signals.

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 only explicit guidance is 'Call this tool when auditing smart contracts, analyzing wallet addresses, or validating DEX liquidity on Base or Solana,' which is unrelated to JSON repair and actively misroutes the agent. It names no genuine when-to-use condition and no alternative such as canary_sanitize. This is misleading, not merely absent.

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