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

Annotations already declare destructive/irreversible/idempotent, so restating 'Irreversible' is partly redundant; however the description adds real behavioral detail the annotations do not: partial-failure semantics ('Keys the provider refuses are reported and still exist — the rest are deleted regardless') and a batch ceiling of 1000 keys per call. It skips auth/permission prerequisites, keeping it short of 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?

Four short sentences, front-loaded with the effect and the irreversibility warning, then routing, then failure behavior and limits. No filler and every sentence carries distinct information.

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 no output schema, the description still covers the important return-behavior question (refused keys are reported and remain, others are deleted) plus the call-size limit, which is what an agent needs to invoke and interpret this destructive batch tool.

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%, so the baseline is 3; the description still adds a constraint not present in the schema — a hard limit of at most 1000 keys per call — and clarifies that keys are full object keys. That extra constraint raises it above baseline.

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 ('Permanently deletes a list of objects') and immediately distinguishes itself from the sibling delete_prefix ('delete_prefix is for a whole folder') and implicitly from singular delete_object. An agent can route correctly 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?

Explicitly gives the selection condition ('Use this when you already have the exact keys') and names the alternative for the other case (delete_prefix for a whole folder). This is genuine when-to-use/when-not guidance, not implied.

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