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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the crucial blast radius detail that it destroys TWO bindings plus the stored grant and breaks Ahrefs data for all organization members, not just the caller. The admin-role prerequisite is authorization context the annotations do not carry.

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?

Two sentences, zero filler, and the destructive scope statement is front-loaded before the permission note. Every clause carries operational weight.

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 destructive mutation with no output schema, the description covers what is destroyed, who is affected, and the role requirement. It could go slightly further by noting the operation is not undoable without reconnecting (and which tool re-establishes the connection), but nothing essential is missing.

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?

Single parameter with 100% schema description coverage; the schema already explains projectId and points to list_projects. The description adds no additional parameter meaning, so the baseline of 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?

States a specific verb (disconnect/full disconnect) and precisely enumerates the resource scope: both the Rank Tracker and Site Audit bindings plus the stored grant. This cleanly distinguishes it from sibling disconnects like disconnect_bing and from set_ahrefs_project, which is the inverse operation.

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?

Gives clear context for invocation: it is the 'full' teardown, it affects every member of the organization rather than just the caller, and it 'requires at least the admin role.' It never explicitly names the alternative (e.g., a partial unbind or set_ahrefs_project for rebinding), so it stops short of full when/when-not routing.

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