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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds some useful content semantics — `include: layout` shows where everything sits, `overview` returns a picture, `params.includeHtml` returns a screen's HTML — but says nothing about response size, truncation, pagination, or permission requirements for a tool that spans 14 resource types.

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?

It is front-loaded with the core purpose and packs a lot of per-kind detail into one dense sentence with no filler. The tradeoff is that the telegraphic parenthetical list is hard to scan for 14 kinds, but no sentence is wasted.

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 14-way dispatcher with a free-form nested `params` object, the description only documents `params` fields for two kinds (page/include, design/includeHtml) and otherwise defers to the separate `guide` tool. Given no output schema and open-ended `additionalProperties`, an agent is left guessing the required fields for the remaining twelve kinds — a real gap, though partially mitigated by the explicit pointer to `guide({topic})` in the schema.

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 the baseline is 3, but the schema's own descriptions are near-empty ("What to read.", "The action's fields."). The description meaningfully compensates by attaching content expectations to specific enum values (page → screens/canvas/comments, checks → problems with fixes, comments → summary) and by explaining the two `include` modes, which the schema only labels without explaining.

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 verb+resource ("Read one thing in full") is clear, and the kind list gives concrete evidence of what can be read (screens, canvas and comments, problems with fixes, HTML). However, it is a dispatcher over 14 unrelated resources, and the description never clarifies why a caller should use this instead of the sibling tools named `design`, `find`, or `catalog` — the overlap with `design` in particular is left ambiguous.

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?

No when-to-use or when-not-to-use guidance is given; the caller must infer the right kind from a bare enumeration. There are no stated prerequisites, no exclusions, and no routing to sibling alternatives (find, catalog, design), even though the kind list overlaps with several of them.

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