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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real behavioral context beyond that: results are paged, ordered newest-first, include short descriptions and real prices, and paging requires reusing the same kind and search values.

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?

Purpose and ordering are front-loaded and the pagination rule follows logically. Mostly efficient, though 'Cost follows each model's real price' is a redundant restatement of 'what it costs'.

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 adequately: each item has a name, short description, and cost, sorted newest-first and paged. An agent has enough to call it and continue paging 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% with limit, offset, and search already documented. The description adds a cross-parameter constraint not in the schema: when following nextOffset you must keep kind and search unchanged, which is genuinely useful for correct pagination.

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 image or video models') and clarifies these are generation models currently available. It differentiates reasonably from generateImage/generateVideo, though it does not explicitly separate itself from the similarly named listMedia or listVideos siblings.

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?

Usage is implied (browse model catalog with descriptions and costs) and pagination workflow is spelled out, but there is no explicit statement of when to use this versus listMedia/listVideos or when-not to use it. Adequate but leaves sibling selection to inference.

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