lookup_extended_model_pricing

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

With no annotations, the description carries the whole burden, and it discloses real behavioral context: data provenance (LiteLLM public JSON and OpenRouter /api/v1/models), weekly auto-ingestion, the source='litellm'|'openrouter' row tag, and that the catalog already excludes embedding/image/audio. It stops short of saying what a returned row contains, whether results are sorted or paginated, or how the weekly refresh affects freshness.

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?

It is a single dense block, but it is front-loaded with the catalog's identity and provenance before moving to the (a)/(b) usage cases. The long provider enumeration (Together AI, Fireworks, Replicate, Groq, Cerebras, Perplexity, Bedrock/Azure) is the one stretch that adds bulk faster than it adds decision value.

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 8-parameter, no-annotation, no-output-schema tool, the description covers purpose, provenance and when to prefer it over its sibling, but omits what a row returns, sort order, and the meaning of the three cost/limit parameters. Enough to select the tool, not quite enough to invoke it with confidence.

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 63%, so the schema documents mode, query, source and provider well, and the description largely restates that source semantics without adding syntax. It says nothing about limit, monthly_input_tokens or monthly_output_tokens, leaving three params — two of which imply cost estimation behavior — unexplained in both places.

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 uses a specific verb ('Search') against a specific resource ('extended LLM catalog', ~2300 model/provider combinations) and explicitly distinguishes itself from the sibling compare_token_pricing by scale and curation level. An agent can tell these two apart without opening either schema.

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?

It names two concrete use cases — (a) a model or provider compare_token_pricing doesn't know, and (b) whether OpenRouter routing is cheaper than going direct — and gives example queries like 'cheapest place to host Llama 3.1 405B' and 'what Groq charges for Mixtral'. The alternative is named explicitly, so selection is unambiguous.

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