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

Annotations already declare readOnlyHint, destructiveHint false, and a closed world, so the safety profile is covered. The description adds useful context beyond that: the content is sectioned documentation, and omitting the parameter returns 'all', making it clear this is a static reference fetch with no side effects. It does not describe output format (markdown vs prose) or size, a minor remaining gap.

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?

Purpose and section list are front-loaded and the guidance clause comes last, which is the right ordering. The single long sentence with stacked parentheticals is dense but nearly every clause carries information; the closing 'dashboard_publish's own description is the contract' phrase is the only part that could be trimmed or shortened.

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 one-parameter, no-output-schema reference tool, the description covers what to ask for and why, and effectively doubles as return-value documentation by listing each section's contents. Only the response shape (plain text? structured?) is unstated, which is a small omission for a documentation lookup.

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 already 100%, yet the description still adds real meaning to each enum value: 'kinds' covers panel kinds, their fields, rules and tone; 'layout' covers widths, heights, phones and canvases. That goes well beyond the schema's 'Which section to read' and directly helps an agent pick the right section.

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 states a specific verb and resource ('the full reference for dashboard specs, by section') and enumerates exactly what the tool returns. It distinguishes itself from dashboard_publish by framing that tool as 'the contract' and itself as 'the detail', though it does not explicitly differentiate from other read siblings like dashboard_get or dashboard_read.

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 concrete when-to-use rule: read 'kinds' before writing a spec with an unfamiliar kind, and by extension consult the reference before authoring. It does not state when not to use it (e.g. 'skip this if you already know the contract' or 'prefer dashboard_get for existing dashboards'), so it falls short of full alternative routing.

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