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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new context by disclosing that figures come from AI Gateway's live catalog, signaling fresh external data rather than cached figures.

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, front-loaded with the comparison scope before the input convention. Dense but not padded; the enumerated outputs each carry weight, though the run-on clause makes it slightly heavier than necessary.

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?

An output schema exists, so return values need not be explained, and the annotations carry the safety profile. The description covers what is compared and how to supply models, leaving only minor gaps around sibling selection.

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 all five parameters, establishing a baseline of 3. The description restates the models-id/provider-name convention from the schema and adds little syntactic or format detail beyond it.

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?

Specific verb (compare) plus resource (models), and it enumerates exactly what is compared: cost per request and per month, prices, context window, output limit, release date and knowledge cutoff. This clearly distinguishes it from siblings like estimate_cost or count_tokens.

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?

States the input style (ids or provider names) and that provider names resolve to newest models, which is useful operational guidance. However, it never states when to reach for this over estimate_cost or price_ai_feature, nor any exclusion criteria, so usage is only implied.

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