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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds real value beyond that: an optimistic-concurrency precondition on version, the failure mode when it mismatches, and the fact that replays cannot recover the file. It doesn't discuss permissions or behavior when the file is already gone.

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, zero filler. The irreversible consequence is front-loaded in sentence one's scope statement, and the version precondition follows immediately.

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 destructive write with an output schema and destructiveHint already present, the description covers scope, the key precondition, and irreversibility. Minor gaps remain around permission requirements and the idempotency-key retry interplay, which the schema documents only for idempotency_key itself.

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 only 25%, so the description must compensate for the undocumented params, and it does for the non-obvious one: 'version' is explained as a concurrency guard rather than a plain identifier. space_id and file_id are left to the schema, but their names and the space_id pattern make them largely self-explanatory.

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 file') plus a scope constraint ('from a private Space'), which separates it from space_file_get/create/copy/list by verb alone. It never names an alternative explicitly, so it stops short of full sibling differentiation.

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 description gives a conditional rule for the version argument ('must match the file's current version or the call is refused'), which is useful pre-call guidance. However it never says when to prefer this over alternatives (e.g., no soft-delete/archive option mentioned), nor what permissions or state the caller needs.

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