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

Annotations already declare destructiveHint=true and readOnlyHint=false, so permanence is expected; the description reinforces 'Permanently' and adds two non-obvious preconditions (stop live streams, disconnect connected destinations) that the annotations do not convey. It stops short of describing failure modes or whether the operation is recoverable.

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, each earning its place: action, precondition, and API mapping. The most important information (permanent removal plus prerequisites) is front-loaded.

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-param destructive tool with no output schema this is complete: what it does, what must happen before calling it, and which endpoint it mirrors. Nothing needed to invoke it correctly 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?

Schema coverage is 100% with both UUID parameters documented in-schema. The description only echoes them implicitly via the REST path '(streams/{stream}/destinations/{destination})', adding endpoint-mapping context but no new meaning about the identifiers.

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 ('Permanently remove'), a specific resource ('multistream destination'), and the containment scope ('from a stream'). This clearly distinguishes it from add_destination and update_destination without opening any schema.

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 concrete preconditions: live destinations must be stopped first, and connected destinations must be disconnected in the dashboard. It does not name an alternative tool or explain when to prefer update_destination instead, but the operational gating is clear.

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