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

Annotations only declare destructiveHint=true, but the description adds materially richer behavior: the two-phase preview-before-delete flow, the cascading scope ('everything on it'), the exact-name matching requirement, and irreversibility ('cannot be undone'). These are critical safety behaviors an agent must know before invoking. No contradiction with 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?

Three short sentences, each earning its place: the core destructive action, the two-phase confirmation flow, and the irreversibility warning. The most important fact (permanent deletion) is front-loaded first.

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 destructive, two-phase tool with annotations and a 100%-covered schema, the description covers the essential workflow. Minor gaps: the preview's return structure is not described (no output schema exists), and the failure behavior when confirmName does not match is left implicit. These are small given the schema already instructs the agent to copy the name from the preview.

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 description coverage is 100%, and the schema already documents confirm, confirmName, and dashboardId in detail. The description's mention of 'confirm plus the dashboard's exact name' mirrors the schema rather than adding new semantic information, so the baseline 3 applies.

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 ('permanently delete'), a resource ('dashboard'), and a scope ('and everything on it'). This clearly differentiates it from siblings like delete_view, delete_widget, update_dashboard, and unpublish_dashboard, which either target sub-resources or non-destructive modifications.

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?

The description gives clear operational guidance: calling without confirm returns a preview, and real deletion requires confirm plus the exact dashboard name. It also warns that the operation cannot be undone, serving as an implicit gate. However, it does not explicitly name alternatives or state when not to use it (e.g., 'use delete_view to remove only a single view').

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