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

Goes well beyond the annotations: it discloses that every call is charged in USDC from the configured wallet, that charges are bounded by budget caps, that max_tokens doubles as a spend limit, the per-request price ($0.005, product llm.chat), and that results are third-party data rather than instructions (a prompt-injection warning). Annotations only say readOnlyHint/openWorldHint/idempotentHint=false; the cost and trust model come entirely from the description.

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?

Front-loads what the tool is and what it costs, then stacks constraints and safety notes; nearly every sentence carries load-bearing information. The opening sentence is a dense run-on that packs three distinct facts (pricing basis, spend limit, prerequisite) together, which slightly hurts scannability.

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, and the description does not describe the response shape, but 'chat completion' makes that largely predictable for an agent. Given the payment model, the description covers the material operational facts: cost, cap, budget enforcement, and the untrusted-content warning.

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 coverage is 44% across 9 parameters. The description usefully re-annotates max_tokens as a spend limit and resolves the schema's 'max 32000' against the MCP cap of 4000, and it paraphrases confirm_over_cap's budget semantics. However, seed, stop, top_p, temperature, and response_format get no explanation anywhere, so the description only partially compensates for the coverage gap.

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?

States a specific verb+resource ('Chat completion from maxwell-chat') and immediately scopes it with pricing and the tool's role in the catalog. It differentiates from get_price_quote by naming it as a prerequisite rather than an alternative. It stops short of describing output shape, but the purpose 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?

Explicitly instructs 'Use get_price_quote first to see the exact price,' giving a concrete precondition rather than leaving sequencing to inference. It also states the MCP-specific constraint (max_tokens at most 4000) that governs when the call will succeed. No when-not-to-use case is given, but the paid nature and budget caps imply the boundary.

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