vk_delete_raw

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

Annotations already mark this as destructive (destructiveHint=true, readOnlyHint=false), so the description's job is lighter. It adds useful behavioral context beyond the annotations: both confirmation flags are mandatory, the method must be DELETE, and it returns either a success JSON envelope or an error envelope. It could mention irreversibility or auth requirements, but the confirmation flags and destructive hint cover the main safety concern.

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 description is front-loaded with the core purpose, then immediately gives the key constraint ('DELETE only') and required safety flags. The Args section is terse, organized, and maps cleanly to the schema. No sentence is wasted, and the return envelope is stated at the end without unnecessary elaboration.

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?

The description covers all invocation essentials: path format, method, host, query, body, mandatory confirmation flags, and expected return shape. The output schema exists, so return values need no further detail. It falls just short of full completeness because it does not explicitly route an agent to vk_delete_method for catalog-managed paths, nor does it state auth prerequisites or irreversibility beyond the confirmation flags.

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 carries the full burden for parameter semantics. It successfully explains all seven parameters: path format, method constraint, host default behavior, query/body purpose, and the mandatory truthiness of both confirmation flags. This is especially valuable because the schema defaults both confirm flags to false, and the description overrides that by marking them required.

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 states a specific verb and resource: 'Delete data at ANY path, including paths not in the catalog.' This clearly distinguishes the raw delete tool from sibling tools like vk_delete_method, and explicitly constrains the method to DELETE. An agent can immediately understand what operation this tool performs and how broad its scope is.

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 explicit invocation constraints: DELETE only, confirm_write=true, and i_understand_this_modifies_data=true. It also clarifies that the tool works outside the catalog, implying it is for raw or non-catalog paths. It does not explicitly name alternatives or state when not to use it, but the scope is clear enough from the ANY-path wording.

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