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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely new behavior: pricing units per model class, unit_size for character-priced TTS, and pagination semantics (total, truncated, next_offset). The catalog-ranking instability caveat lives in the offset schema field rather than the description, so it is slightly under-surfaced here.

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?

Three sentences, front-loaded with what the tool returns, then when to call it, then how the page works. No filler, and the pagination guidance is placed last where an agent reads it after deciding to call.

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 takes on the burden of describing the return shape (one page, total, truncated, next_offset) and does so. For a 4-param, zero-required, read-only listing tool, an agent has everything needed to call it and to handle the response correctly.

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 75%, so the schema does most of the work, but the description adds real meaning: it enumerates the type values and explains how to react to a truncated result ('narrow with type or search, or call again with offset=next_offset'). That is a usage pattern, not a restatement of the field docs.

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 ('List available AI models') plus exactly what each entry carries: type, capabilities, and pricing in credits. It also sub-divides pricing models (per-1K-token text models, reference-priced generation, character-priced TTS), which lets an agent tell this apart from get_model and the generation siblings without opening any 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?

Gives an explicit trigger: 'Use before chat or generation when the user asks for a specific model or wants to compare options or prices,' which ties it to concrete sibling workflows. It does not name the obvious alternative (get_model) for when a slug is already known, so the exclusion half of the guidance is left implicit.

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