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

Annotations cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds substantial context beyond them: async job mechanics (jobId + free pollUrl), typical latency (8000 ms p95), and full pricing (0.002 USDC/1k tokens, 0.03 cap). This is exactly the kind of operational detail an agent needs before calling a paid async endpoint.

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 the return value, then usage, exclusions, pricing, and async mechanics in tight sentences. The pricing parenthetical ('clients without upto pay the cap') is slightly cryptic, keeping it just under perfect.

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?

For an async paid LLM endpoint, the description covers the model, output, usage boundaries, pricing, and polling workflow; annotations cover safety and an output schema exists for return values. Nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so the schema already documents messages, maxTokens, and temperature in detail, including defaults and bounds. The description adds no parameter-specific syntax or semantics, so the baseline 3 applies.

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 and resource ('chat completion'), names the exact backend model ('IBM Granite 4.0 Micro on Workers AI'), and discloses the return payload ('JSON ... with token usage'). It is clearly distinguishable from the sibling llm-chat_v1_status and the other domain tools.

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?

Gives explicit when-to-use ('summaries, extraction or classification and can poll an async job') and explicit when-not-to-use ('frontier model, tool calling or streaming'). The alternative condition is fully spelled out, leaving nothing to inference.

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