notebook_delete

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description merely repeats the destructive action ('Delete') without adding any context beyond the annotations: nothing about permanence/irreversibility, whether deletion cascades to definitions, permission requirements, or failure behavior. No contradiction, but zero added behavioral value.

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 words, one sentence, zero wasted content, and the core action is immediate and front-loaded. It is appropriately compact for a simple delete primitive, though the brevity edges toward under-specification rather than deliberate conciseness.

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 2-parameter tool with no output schema and annotations covering mutation/destruction, the essential calling information is present: parameters are documented in the schema and the safety profile is in the annotations. The gap is that for a destructive operation, an agent would benefit from knowing whether deletion is permanent/reversible or has cascading effects, which neither the description nor annotations disclose.

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% with both required parameters (workspaceId, notebookId) documented, so the schema carries the parameter burden; the description adds nothing about parameter semantics. Per the high-coverage baseline, a 3 is appropriate, though the schema descriptions ('The notebook ID', 'The workspace ID') are themselves minimal restatements of the parameter names.

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?

"Delete a notebook" states a specific verb and resource, and the verb 'delete' distinguishes it from notebook_list/get/create/update/run siblings. However, it is essentially a word-order rearrangement of the tool name itself, adding no semantic detail beyond what the name already encodes, and it does not differentiate it from other *_delete sibling tools except by resource name.

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 provides no guidance on when to use this tool versus alternatives, no exclusions, and no prerequisites. Nothing indicates e.g. whether the notebook must not be running, whether a running notebook should be stopped first via notebook_cancel_run, or that notebook_get_definition should be called first if a copy is needed before deletion.

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