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

Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds real value on top: a mandatory preview step, single-use confirmationToken with a ten-minute expiry, the required admin profile and pod write switch, and the fact that the input cell limit is validated before the call. That is exactly the pre-flight information an agent needs before firing a destructive write.

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 opening sentence is well front-loaded, but the final sentence repeats the preview/confirm/token flow already stated two sentences earlier, and a raw documentation URL (with a truncated-looking anchor) is wedged mid-paragraph. Redundancy plus a misplaced link costs it a point.

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, non-idempotent write with ten parameters and no output schema, the description covers authorization and the confirmation flow well but says nothing about what comes back or what happens next — whether recomputation is synchronous or returns a job id to poll via check_job_status, and what existing insights are replaced. That is a meaningful gap given no output schema exists to answer it.

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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by explaining the preview → confirm:true + confirmationToken handshake and its single-use, ten-minute lifetime, and by noting the input cell limit that governs how large a slice is accepted. It does not explain the pov/rows/columns exact-member constraint beyond what the schema already says.

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?

Names a specific verb and resource ("Recomputes application insights") plus the mode used (FORCE_RECOMPUTE), which is far more than a restated name. It distinguishes itself implicitly from the read path by tying the call to "fresh insights after reviewing the exact slice," but never names read_insights as the read-only alternative, so an agent must infer the boundary.

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 an explicit trigger ("when the user wants fresh insights after reviewing the exact slice") and lays out the prerequisites: preview, confirm:true, Admin profile, pod write switch, plus Administrator or IPM Manage on Oracle. It stops short of naming alternatives or stating when not to use it (e.g. plain read of existing insights via read_insights).

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