delete_instance

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

With no annotations present, the description carries the full burden and does well: it explicitly labels the operation destructive, names the confirm safeguard, and discloses that key files are backed up first. Gaps remain on what "key files" means, where backups land, and whether the deletion is reversible or how it behaves without confirm.

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 with the destructive warning and confirm requirement front-loaded. Every clause carries information; nothing is padded.

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, unannotated tool with no output schema, the description covers the essentials of danger and the confirm gate. It falls short on consequences: no mention of what happens if confirm is omitted, where backups go, or whether the deletion can be undone.

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%, so the description must compensate. It usefully explains that confirm must be true (a boolean whose required value is not inferable from the schema), but the required id parameter is never mentioned beyond the phrase "instance directory."

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 an instance directory"), leaving no ambiguity about the operation. No sibling tool performs deletion, so it is implicitly distinguishable, though the description does not explicitly contrast with alternatives like export_instance or backup_world.

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?

Provides one hard precondition ("requires confirm: true"), which is real usage guidance. However, it never says when a caller should prefer alternatives (e.g., exporting or backing up an instance first) or what the guard is protecting against.

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