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

Annotations already cover the read-only/idempotent safety profile, and the description adds the non-obvious behavior that matters: the free tier redacts vendor/model names and exact prices while PRO returns them, and that units vary by modality (per 1k tokens, per image, per second, per 1k characters). That tier-gating and unit disclosure is exactly the kind of context schema and annotations cannot express.

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 core capability, then tier behavior, then units, then examples — a logical order with little waste. It is dense but the pricing/paywall URL sentence sits close to promotional, costing it a point against strict conciseness.

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?

With no output schema, the description carries the return-shape burden and does so: it lists the aggregate fields produced (counts, ranges, spread ratio) and the per-offer detail including channel, plus how output differs by tier. An agent has enough to call it and interpret the response without reading source.

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; the description earns above that by explaining the unit semantics behind `direction` (per 1,000 tokens vs per image/second/minute/character) and by demonstrating the model_name vs model_family split through examples. It doesn't clarify `limit` or the 200 maximum, but the schema already does.

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?

Opens with a precise verb+resource+scope: 'The same model, or a whole family, priced across every vendor that sells it', and then enumerates the exact outputs (cheapest/highest offer, vendor count, spread ratio, per-offer channel). This clearly separates it from siblings like get_model_detail, get_vendor_catalog or get_price_history, which deal with single models, catalogs or time series rather than cross-vendor comparison.

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 two worked examples explicitly show the two modes of use (model_name for a single model, model_family + direction for a family aggregation), which resolves the main ambiguity an agent would face. It stops short of naming when NOT to use this tool or which sibling to pick for historical or per-vendor data, so no exclusions are stated.

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