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

Annotations already declare readOnly/idempotent/non-destructive, so the description adds the genuinely non-obvious bits: no API key required, zero cost, and how the 'default' marker governs behavior when no model is named. It omits pagination/return-size behavior, but limit is schema-documented.

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 dense sentences, front-loaded with what is returned before the integration hint. Every sentence carries information, though the parenthetical about video fields (resolutions, clip lengths, sound) is slightly list-heavy.

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?

No output schema exists, and the description compensates by enumerating the return payload shape (id, price, plus category-specific details). Combined with the default-model semantics, an agent has everything needed to call and interpret it.

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 all four params are already documented, including the audio-holds-speech-and-music enum nuance. The description mainly restates filtering rather than adding new parameter mechanics, 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?

Specific verb + resource ('List the AI models GenMagic runs') with ordering ('newest first') and the returned fields spelled out per category. It also distinguishes itself from the generate_* siblings by explaining that ids from here are passed as 'model' to those tools.

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?

Clear context for use: filter by category/search, and use the entry marked default when no model is named (including the text-type nuance). It names the sibling tools that consume the output but gives no explicit when-not-to-call guidance or caveats about calling it repeatedly.

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