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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety bar is low. The description adds genuinely useful caveats beyond that: the list is sourced live from the Canvas catalog, is not provider verification, and is NEVER a paid approval - important for an agent that might otherwise treat the output as authorization.

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 tight sentences with the mode behavior front-loaded and the caveats trailing. The opening 'Offline provider-neutral Canvas continuity library' is the weakest part — jargon that delays the actionable content — but it is only one clause.

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-only capability listing with no output schema, the description covers purpose, mode semantics, and freshness/provenance caveats. It stops short of hinting what a returned entry contains (model keys plus descriptors), which would help an agent chain into aimixer_canvas_describe_model or aimixer_canvas_apply.

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 0%, so the description must carry the load, and it does: omitting model_key returns a list filtered to models accepting a first frame, while passing it targets one exact video model. Only downside is that it doesn't hint at valid key formats or where keys come from (e.g., a find_models sibling).

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?

The second sentence nails the resource and behavior: pass model_key to describe one exact video model, omit it to list Canvas models whose descriptor accepts a first frame. That is concrete enough to distinguish it from generic siblings like aimixer_canvas_capabilities or aimixer_canvas_find_models, though it never names those alternatives and the leading phrase 'Offline provider-neutral Canvas continuity library' describes a library rather than a tool, adding a bit of noise.

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?

The description clearly explains the two modes (keyed lookup vs full list), which is real usage guidance. However, it gives no guidance on when to choose this over neighboring tools such as aimixer_canvas_capabilities, aimixer_canvas_find_models, or aimixer_canvas_describe_model, which is the harder selection problem in this cluster.

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