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

Annotations only cover the safety profile (readOnly/idempotent/non-destructive), and the description goes well beyond them: it discloses the tier gating (free tier returns counts, ranges and redacted samples; PRO key unlocks vendor names, model names and exact prices) and the unit semantics for token vs. non-token modalities. That is exactly the behavioral context an agent cannot get from structured fields.

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-loaded with the capability statement, then tier/unit semantics, then two compact examples. Every sentence carries information, though the paid-tier pitch sentence is denser than strictly needed for selection.

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 carries the return-value burden and does so: it names the aggregates (cheapest/dearest offer, vendor count, spread ratio) and the per-offer channel detail, and flags that the free tier redacts them. Nothing material for correct invocation or interpretation 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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning: it clarifies the model_name vs. model_family distinction via examples, implies the direction dimension (input/output), explains the pricing units (per 1,000 tokens, per image, per second, per minute, per 1,000 characters), and explains what _atom_api_key unlocks. It does not explain limit/pagination behavior 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 description states a specific verb+resource at a specific scope: pricing one model or a whole family 'across every vendor that sells it', and enumerates the outputs (cheapest/dearest offer, vendor count, spread ratio, per-offer channel). This is readily distinguishable from siblings like get_model_detail, search_models, or list_vendors.

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?

Two concrete natural-language examples map intent to parameters ("Cheapest place to run Llama 3.3 70B" -> model_name=..., "Qwen family output prices" -> model_family + direction), which gives clear context for when to use which parameter. It lacks explicit when-not guidance or naming of an alternative sibling for single-model lookups.

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