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

Goes well beyond destructiveHint=true and readOnlyHint=false by disclosing the review lifecycle, the auto-approve rule when kind is on the instructions' onItsOwn list, who may be named reviewer ('never you'), and the constraints on re-proposing with an id. It does not spell out reversibility or what happens if the reviewer rejects, which keeps it out of the top band.

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?

The opening sentence is well front-loaded, but the body is roughly 300 words of tangled clauses ('comes back doing, approved and held by you', 'a kind someone else gave a task never approves it on its own') whose grammar obscures rather than compresses the rules. Several sentences could be shortened without losing meaning.

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 12-parameter mutation tool with an output schema, the description covers the full lifecycle, the decision fields (approvedText, decision), the follow-up tools and the auto-approval edge cases, so an agent knows how to call it and what to do next. Missing only rejection behavior and the required why field.

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 75%, and the description adds genuine conditional logic the schema lacks: title plus workspaceId, or parentId alone for the workspace; with id, the task must be 'free or yours' or be your own proposal's draft; reviewer defaults to your own person and can never be you. It doesn't mention why, links or audience, leaving some parameters to the schema alone.

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?

First sentence names a specific verb and resource: propose an out-of-workspace action (post, email, booking) with draft, approve verb and kind. That distinguishes it from sibling task_create and from task_decide (the reviewer's side). It loses a point because the later sentences bury the core purpose under lifecycle jargon and make the tool's identity harder to grasp at a glance.

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?

Explicitly states the trigger ('Before acting outside the workspace... propose it') and the stop condition ('Stop there; on a later run, workspace_load and task_get show the decision'), which is real workflow guidance. It doesn't name sibling alternatives such as task_create or task_decide, so the agent must infer that this tool is the pre-action path.

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