delete_document

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

Annotations already convey destructive and non-read-only behavior, so the description goes beyond them by clarifying that only unposted documents qualify and that posted documents require unposting first. It also explains the party_type collision behavior, which is non-obvious and valuable. It doesn't explicitly state that deletion is permanent or idempotent, but the destructive and idempotent hints cover that baseline.

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 core action is front-loaded, the critical posted/unposted caveat follows immediately, and the Args section maps cleanly to the schema properties. Every sentence earns its place, including the brief rationale for the constraint.

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, conditional delete operation, the description covers the object type, the precondition (unposted), the prerequisite action for posted documents, the parameter semantics, and the edge case around party_type. With an output schema present and annotations covering safety, nothing material is missing for an agent to invoke this correctly.

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 0%, and the description fully compensates by explaining each parameter: document_type lists valid values, id gives an example format, and party_type describes its conditional necessity and collision scenario. This is exactly the kind of semantic context the schema does not provide.

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?

The description states a specific verb ('Delete') and resource ('UNPOSTED customer invoice, vendor bill, employee voucher, or credit note'), with explicit scope. The qualifier 'UNPOSTED' cleanly differentiates this from unpost_document and makes the tool's sole purpose unmistakable.

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?

The description explicitly tells agents when not to use this tool ('Posted documents are on the books') and names the alternative path ('unpost_document first'). It also notes a blocking condition ('payments block unposting'), giving concrete routing guidance without leaving room for guessing.

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