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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the main gap the description fills is the clarification that opening the editor 'does not save or load a website until the user acts' — resolving the apparent tension between a non-read-only tool and a call that has no immediate effect. It still doesn't say what the call returns or what happens if the editor is already open.

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, mode-switching rule front-loaded after the action statement, and no filler. Each sentence carries a distinct piece of information: action, mode selection, side-effect timing.

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-optional-parameter UI-opening tool with no output schema, the description covers action, both modes, and side-effect timing, which is most of what an agent needs. The only meaningful omission is the interaction with the sibling save_task_editor and behavior when the editor is already open.

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 0%, so the description must carry the semantics and it does the important part: omitting uuid means create mode and workspaceId selects the target workspace. It leaves gaps — whether workspaceId is ignored or rejected when uuid is supplied, and nothing about uuid format beyond the schema's 'format: uuid'.

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 and resource ('Open ... task editor') and distinguishes edit mode (with uuid) from create mode (without uuid), which separates it from the sibling save_task_editor. The word 'existing' in the first sentence is slightly at odds with the create case described next, adding a small wrinkle an agent must resolve.

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 rule 'Omit uuid to create a task in workspaceId' implies when each mode applies, but usage is framed entirely through parameters rather than naming the flow: no explicit statement that save_task_editor is required to persist, and no when-not guidance such as what happens if the editor is already open.

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