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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the risk profile is covered. The description adds useful async behavior (job-id polling vs fire-and-forget queueing), but never states that writeMarkup overwrites existing markup for that size, nor any auth or side-effect details beyond the annotations.

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?

Front-loaded with the polling rule, then clean per-action bullets with params inline. The opening sentence is dense and mixes the three actions with the polling caveat, which slightly hurts scanability, but there is little wasted text.

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 multi-action dispatcher with nested params and no output schema, the description covers the key unknowns: per-action arguments and the async return/polling contract. Missing only overwrite semantics for writeMarkup and any per-action error or permission notes.

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?

The schema only exposes generic 'action' and 'params' objects, so the description carries most of the semantic load by enumerating each action's path/body arguments, including the full size enum and the optional device_model. Coverage is effectively complete, but field-level typing and required-vs-optional status are still partly implicit.

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 description names three concrete operations (writeMarkup, startPreview, startRefresh) and states what each does with its resource (plugin markup / plugin instance), so an agent knows exactly what will happen. It does not explicitly contrast with the sibling AccountMarkupReadTool, though it references getPreview/getRefresh as the read counterparts.

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?

It gives a real decision rule: startPreview and startRefresh on a polling instance return a job id to poll, while any other refresh queues a render and yields nothing to poll. That is actionable routing guidance. It stops short of saying when to prefer writeMarkup versus other authoring tools.

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