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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds real behavioral depth beyond them: exactly what is removed (disk + registry), a mandatory confirmation gate, the ownership/authorization boundary, and the not-found failure behavior for missing paths.

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, front-loaded sentences: purpose first, then the confirmation gate, then the parameter provenance, then the ownership/error constraint. Nothing is redundant or 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?

An output schema exists, so return values need not be explained. The description covers the remaining agent-critical concerns for a destructive two-parameter tool: authorization scope, confirmation requirement, and not-found behavior.

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 100%, so both 'path' and 'confirm' are already documented in the schema, including that confirm MUST be true. The description restates the same requirements (confirm=True, path from data.upload) without adding format or edge-case detail, so baseline 3 applies.

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 uploaded file'), plus scope ('from your account (disk + registry)'), which cleanly separates it from the sibling data.upload and data.inspect_file. An agent can tell what it does without opening the 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?

Gives the prerequisite ('Requires confirm=True') and the input provenance ('Pass the path returned by data.upload (file.path)'), plus a constraint ('Only your own uploads can be deleted'). It stops short of naming alternatives or explicit when-not conditions, so it is clear context rather than full routing guidance.

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