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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes well beyond them: it states the permission requirement (owner or shared with edit rights), that audience is re-checked against the target version's content, that versions built on unowned data or carrying personal data stay private or are narrowed, and that readers see the change on their next open. What it never says is whether the prior live version is preserved (i.e., how recoverable this destructive change is) or whether a promoted draft is consumed.

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 sentences, front-loaded with the action, then the accepted inputs, then the side effects, with no filler. The first sentence is long and clause-heavy, which slightly hurts scannability, but every sentence carries content an agent needs.

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 two-parameter destructive mutation with no output schema, the description covers permissions, input sources, audience re-evaluation side effects, and visibility timing. The remaining gap is the response shape — it says only 'the reply says so' — leaving the agent without a concrete idea of what the promotion reply contains beyond the audience adjustment.

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so the baseline would be 3, but the description adds real meaning: it explains that 'draft' refers specifically to the unpublished draft produced by dashboard_publish or dashboard_patch, and that version numbers are drawn from dashboard_versions. That is interpretive context the schema's own property descriptions only partially convey.

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 (make a dashboard version the live one) and explicitly identifies which version can be promoted: the draft written by dashboard_publish/dashboard_patch with draft: true, or any number from dashboard_versions. It implicitly separates itself from dashboard_publish and dashboard_patch by naming them as producers of the input rather than alternatives, though it never distinguishes itself from the similarly named dashboard_promote or dashboard_rollback.

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?

Usage context is clear: use it to promote a draft or an arbitrary historical version to live, and the note 'exactly as a rollback is' signals the relationship to the rollback path. What is missing is an explicit statement of when to prefer dashboard_rollback or dashboard_promote instead, so the agent must infer the boundary between these three siblings.

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