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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered structurally. The description adds a genuine workflow dependency — that preview/refresh results only exist after another tool has started a job — which is context the annotations cannot convey. It stops short of describing readiness/error states or rate limits.

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?

The opening summary sentence is a fragment ('A private plugin's markup by size, and...'), which is slightly awkward, but the per-action bullets are densely structured and front-load the operation name followed by its parameters. Every line carries information; there is no filler.

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?

There is no output schema, yet the description says only that getPreview/getRefresh return 'the result' without indicating the return shape (markup content, image URL, render status). For a three-operation read tool this leaves the agent knowing how to call it but not what to expect back, or how a pending/failed job manifests.

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 defines a generic 'params' object with no per-property documentation, so the description carries the parameter burden and does so well: it names plugin_setting_id, size and id per operation, flags them as path parameters, and enumerates the size enum values (markup_full, markup_half_horizontal, ...) that appear nowhere in the schema.

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 the resource (private plugin markup) and enumerates the three operations it exposes, with the scope of each sub-action stated. It implicitly points at its write counterpart ('the Change markup tool') rather than naming the sibling AccountMarkupWriteTool, so differentiation is clear in substance but not exact in naming.

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 tells the agent that getPreview/getRefresh are for retrieving results of jobs 'started with the Change markup tool', which gives real sequencing guidance rather than mere implied usage. What is missing is any exclusion or fallback guidance (e.g., what to do if the job has not finished, or when to prefer readMarkup over a preview).

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