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 covered. The description adds useful publish semantics, but it omits important behavior such as expected_sha256 concurrency checks, recursive deletion effects, the 50-target limit, and permission requirements.

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 single sentence is front-loaded and free of filler, but it is undersized for a destructive bulk operation with four parameters. The semicolon clause packs important publish behavior, yet the overall brevity leaves critical details unaddressed.

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?

There is no output schema and annotations only cover safety hints. For a destructive tool with 0% schema coverage and four parameters, the description should explain target semantics, recursive behavior, bulk limits, and concurrency guards, but it does not.

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 description coverage is 0% and the description names none of the four parameters. It does not explain workspace, build_id, targets, recursive, or expected_sha256, leaving the agent with no semantic guidance beyond the raw schema.

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?

The description uses a specific verb (Delete) and resource (draft files/directories), with a scope qualifier that separates it from live content changes. It does not explicitly name sibling alternatives such as files_edit or files_write, but the core action is clear.

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?

It implies when deletion applies by saying draft files/directories and noting live changes only occur on publish. However, it gives no explicit when-to-use guidance versus files_edit, files_write, or other deletion tools, and no prerequisites are stated.

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