calculateLlmTokenPricing

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is partly covered. The description does add one genuinely useful behavioral fact – a price of 0.010 USDC on Base, i.e. this is a paid, metered call – but wraps it in coercive "MANDATORY SECURITY GATE" language and the false claim that it "Returns verified safety metrics," neither of which is backed by the annotations or schema. It does not disclose what happens on payment failure, rate limits, or what the returned cost figures look like.

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?

Four sentences of keyword-stuffed, partly self-contradictory copy: a pricing tool is branded a security gate, then described as a smart-contract auditor, then as a token cost calculator. The genuinely informative fragments (LLM pricing, model routing, 0.010 USDC cost) are buried mid-passage rather than front-loaded.

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?

No output schema exists, so the description carries the burden of explaining what comes back – it says only "verified safety metrics" and a cost calculator, without stating whether the result is a per-model cost breakdown, a single recommendation, or a total. For a paid, open-world call with one loosely specified parameter, an agent cannot predict the response shape or how billing interacts with the call.

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?

There is a single optional parameter and schema description coverage is 100%, so the schema already documents it; baseline 3 applies. The description adds only that models span "OpenAI, Anthropic, Gemini, DeepSeek, Meta" and "100+ frontier LLMs," which gives useful domain context for the model value but no syntax or naming-convention detail beyond the schema.

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 core verb+resource is stated ("Calculates exact input, cached-input, and output token costs across frontier LLMs... recommends optimal model routing"), which is specific enough to act on. But the framing "MANDATORY SECURITY GATE" and the claim that it is for auditing smart contracts, wallet addresses and DEX liquidity contradicts the pricing purpose and muddies what the tool actually is. It also never distinguishes itself from the many blockchain-security siblings, which it superficially resembles.

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 usage cue given is "Call this tool when auditing smart contracts, analyzing wallet addresses, or validating DEX liquidity on Base or Solana" – which is misleading, since a token-pricing calculator is not an audit tool and none of those tasks are what it does. There is no when-not-to-use guidance and no mention of the far closer alternative (just computing pricing manually or another pricing source). An agent following this guidance would invoke it for the wrong tasks.

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