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

Goes well beyond the annotations by disclosing duplicate suppression (already_sent), the connection-owner permission constraint (not_connection_owner), the multiple-account branch returning workspace_connector_ids, and the outcome taxonomy with user-facing messaging rules for needs_reconnect/failed/unconfirmed. One nuance keeps it from a 5: the annotation idempotentHint=false sits slightly at odds with the stated behavior that a repeated call for the same document sends nothing, and it never says whether a successful send can be undone in Qonto.

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?

Front-loaded correctly: purpose, then precondition gate, then parameters, then outcome handling. It is somewhat long and repeats the 'sends nothing' clause across three scenarios, but each paragraph maps to a distinct decision the caller must make, so little is genuinely wasted.

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 an open-world, non-idempotent write with an output schema and full schema coverage, the description supplies everything the agent needs: gating conditions, parameter disambiguation, every outcome branch, and required user messaging. Return-value shape is covered by the output schema, so no narrative duplication is needed.

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 baseline is 3, but the description adds real meaning: document_id is the Well document PDF and never an invoice id, workspace_connector_id is only for the multi-account case, and workspace_id is described by the token-authorization condition. That is useful disambiguation beyond the field descriptions rather than repetition.

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 and destination: send one Well document to the workspace's connected Qonto account as a supplier invoice. It is immediately distinguishable from sibling uploaders like well_upload_document or well_upload_statement_content because the destination (Qonto) and the artifact (a Well document acting as supplier invoice) are both named.

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 precondition sequence: read well_get_connector_coverage with slug "qonto" first, and only call when connection_status is enabled/processing or a projected error has non-null sync_health, otherwise list documents and tell the user nothing was sent. It also routes the workspace_id decision (single vs. multi-workspace token) and the connector-choice branch, leaving little to inference.

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