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

Goes beyond destructiveHint=true by disclosing the cascade scope (folders, sheets, pages are all removed), the user-confirmation expectation, and the recovery path via space.restore. It leaves open whether restore is time-limited (trash retention) and how the confirmation is actually enforced, so not a 5.

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 doing distinct work: consequence, required precondition, and recovery option. The destructive scope is front-loaded before the procedural instruction.

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?

With an output schema present, return values need no explanation, and the description covers destruction scope, confirmation behavior, and reversibility. The one ambiguity is mechanical: whether the tool itself prompts the user or the agent must obtain confirmation, which an agent might need spelled out.

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?

There is one parameter (spaceId) with 0% schema description coverage, and the description never mentions it or its expected form. The integer type and required flag in the schema make it largely self-evident, so this sits at the baseline rather than being penalized heavily.

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 ('Delete a space') and immediately scopes the operation ('with every folder, sheet and page in it'), which distinguishes this cascade delete from sibling deletes like folder.delete or page.delete. The reference to space.restore further pins its role in the sibling set.

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 tells the agent to describe the contents before invoking and names space.restore as the undo path, which is clear usage context. It stops short of saying when NOT to use it (e.g., deleting an individual folder instead of the whole space), so it is not a full 5.

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