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

Annotations only declare destructiveHint=true; the description goes well beyond by disclosing that this is a WRITE that mutates accounting records, that deletion cascades to journal entries, that deleted documents are unrecoverable, and that the request is non-idempotent and must not be blindly retried. That is exactly the extra behavioral context the annotation bar leaves room for.

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-loads the critical WRITE warning and keeps every clause load-bearing (safety, cascade, retry rule, confirmation, endpoint). It is dense and slightly telegraphic, but there is no filler to cut.

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 single-parameter destructive tool with no output schema, the description covers everything an agent needs: what it destroys, the side effect on journal entries, irreversibility, the idempotency caveat, and the confirmation step. Nothing material is missing.

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% and the ids parameter is already documented, including the pointer to cashctrl_list_orders for obtaining ids. The description's 'by id' adds nothing beyond the schema, so the baseline 3 applies.

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 (DELETES) and resource (orders), then enumerates the concrete scope: invoices, quotes, purchase documents. It also discloses the cascade (the journal entries they created) and the transport (POST /order/delete.json), which lets an agent distinguish it from cashctrl_delete_journal_entries and cashctrl_update_order_status without opening any schema.

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 explicit operating context: confirm the ids with the user first, and check the result before retrying because the request is never repeated. What it lacks is any routing to an alternative (e.g., when to delete the journal entry directly via cashctrl_delete_journal_entries instead), so it stops short of full when/when-not guidance.

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