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

Annotations already flag destructive/openWorld/non-idempotent, and the description adds a substantial protocol on top: preview first, then confirm: true with a confirmationToken that is single-use and expires in ten minutes, plus productionPod and productionApprovalId from a second security approval. It also warns that saved snapshots and repeat exports can miss new forms and that current inventory must be compared.

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 purpose is front-loaded, but the middle section lurches into exportCategoriesArtifactsV2 specifics (snapshotName, categories, selectedArtifacts, inventory comparison) that read as notes for one operation rather than a general write tool. Those sentences are also restated awkwardly by the later 'For a write, I require a preview first' sentence, which duplicates the earlier confirm instructions.

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 12-parameter, nested-object, destructive, open-world tool with no output schema, the description covers the risky parts well: the approval/token flow, the safety alternatives, and the catalog-id dependency on list_rest_operations. The gap is that it never says what a call returns or how to interpret results (especially for batch operations like clearDataSlices or lcmImportV2), which the absent output schema would otherwise require.

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 confirming baseline is 3; the description earns above that by explaining the preview/confirm/token flow that governs the confirm and confirmationToken parameters and by pointing operationId at list_rest_operations. It also adds operational constraints not in the schema ('Folder paths end with /', 'An omitted selection exports the whole category'), though these apply to only a couple of the 70+ catalog entries.

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?

Opens with a specific verb+resource and scope: 'Calls one PUT, POST or DELETE operation of the Oracle EPM REST API that is not a job, by catalog id.' It immediately carves out the boundary versus epm_rest_read (reads) and epm_rest_run_job (jobs), and frames itself as the escape hatch when dedicated tools don't cover a change.

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?

'Use it for other changes the dedicated tools lack' plus 'Change sets are the safer option for member edits and production substitution variables' gives a real use-vs-alternative rule, and 'Only write operations are reachable here' sets the exclusion. It stops short of naming the specific dedicated siblings (clear_data_slice, import_data_slice, update_substitution_variable) that should be preferred, leaving the agent to map the catalog.

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