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

Annotations already cover safety (readOnly, idempotent, closed-world), and the description adds genuinely useful output behavior: results are ordered cheapest standard price first, an official list price is included, and discounted tiers are labelled by type. With no output schema, this return-shape detail is the main behavioral payload, though it says nothing about pagination, result caps, or behavior when a model name is ambiguous.

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?

Two sentences with no filler, and the resource scope is front-loaded before the usage hint. The first sentence is dense with a long clause list, but each clause carries distinct information about returned price fields.

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 a single-param read tool with no output schema, the description supplies the essential return contract — sort order, price dimensions, tier labels — which is what an agent needs to interpret results. Minor gaps remain around result limits and ambiguous model-name handling.

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?

Only one parameter and the schema already documents it at 100% coverage with concrete examples ('Claude Opus 5.5', 'deepseek/deepseek-v4.1-flash'). The description adds no additional meaning about accepted formats or matching behavior, so 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 — all sellers' prices for one LLM model — and enumerates the exact price dimensions returned (input, output, cached-input per 1M tokens, plus labelled tier prices). This is clearly distinguishable from siblings like search_models (discovery) and estimate_cost (cost computation).

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 an explicit usage context — 'Use it to answer where is X cheapest?' — which tells the agent the decision this tool serves. It does not, however, name or exclude the sibling alternatives (search_models, estimate_cost), so routing is implied rather than fully specified.

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