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

The annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is covered; the description adds little beyond restating the confirmation flag that the schema already documents. Useful extra context is limited to the REST endpoint mapping and the fact that files are statements/receipts; it says nothing about what ingestion does (parsing, dedupe, draft state) or any file count/size limits.

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 short front-loaded sentences with the core action first, then the endpoint mapping, then the hard prerequisite. Nothing is padded, though the REST route reference earns only marginal space for an agent that cannot call REST directly.

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 mutation with no output schema, the description never says what the agent gets back or what state the session lands in after ingest (are transactions created? queued for commit_onboarding?), nor any constraint on file volume or accepted content types. An agent can fire the call but cannot predict or verify the outcome from this text.

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 75% and sessionId, confirmation and idempotencyKey are documented in the schema; the description's "statement/receipt files" adds semantic narrowing on what belongs in the undescribed files array. It adds nothing about batching, per-file requirements, or how contentBase64/contentType are interpreted, so 3 (schema does the heavy lifting) is right.

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 + resource + target scope: ingesting statement/receipt files into an onboarding session, and pins it to the underlying REST route POST /api/onboarding/:id/ingest. It is clearly distinct from generic siblings like import_from_text or add_transaction_from_photo because it names the onboarding session as the destination, though it does not explicitly say so.

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?

"Requires confirmation: true" gives a hard prerequisite, and the mention of an onboarding session implies this belongs to the onboarding flow rather than the general import path. However, no sibling is named and there is no explicit when-to-use vs when-to-use-something-else (e.g. add_transaction_from_photo, import_from_text, commit_onboarding) guidance, so routing must be inferred.

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