ebill_transmit

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It thoroughly explains the tool's behavior: outbound, draft-by-default, idempotent (never resubmits, at-least-once via stored correlation id), drives the invoice state from issued to sent only from issued, records the business case on acknowledgement, and posts nothing. It also discloses failure modes and the exact reason codes, which is exceptional for agent decision-making.

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 description is dense and detailed, with every sentence contributing critical behavioral or precondition information. It is front-loaded with the primary action and then lists guard order and side effects. While it is longer than average, the structure is logical and the information is necessary given the tool's complexity and lack of annotations. It could be slightly more concise by removing jargon like 'P8' and 'A10', but it remains well-structured.

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?

Given the tool's complexity (multiple preconditions, failure modes, idempotency, state changes) and the absence of annotations or an output schema, the description provides remarkably complete context. It covers prerequisites, failure reasons, idempotency semantics, side effects, and what it does not do (posts nothing). An agent has sufficient information to call it correctly and understand the consequences. The only minor gap is the success return value, but that is a small omission.

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 0%, so the description must compensate. It adds meaning to 'confirmed' (pass confirmed=true) and implicitly to 'idempotencyKey' (via stored correlation id for at-least-once). However, it does not explicitly explain 'workspaceId' and 'deliveryId' beyond the obvious context of transmitting a specific delivery in a workspace. While it provides some semantic value, it is not comprehensive for all four parameters.

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 clearly states the action: 'Transmit a prepared delivery through the owner-gated cloud connector'. It specifies the resource (a prepared delivery), the mechanism (owner-gated cloud connector), and implicitly the eBill context via the guard conditions and sibling tools like ebill_prepare. It distinguishes itself from ebill_prepare (prepares) and ebill_delivery_status (checks status) by focusing on the transmission step and its side effects.

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 gives explicit usage conditions: 'pass confirmed=true or enable the workspace dial' and a detailed guard order listing preconditions that must be met (no connector, needs_biller_pid, needs_confirmation, payload_not_conformant). It does not name alternative tools explicitly, but the guard order effectively tells the agent when it will reject the call. It lacks an explicit 'do not use when' statement, but the context is clear enough.

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