body_workflow_note

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

No annotations are supplied, so the description carries the full disclosure burden. It does convey meaningful behavior, namely that this tool appends to a persistent ledger whose ordering determines auditability, which implies an append-only mutation. It omits whether entries can later be edited or removed, whether workflow_id must reference an existing run, and what happens on failure.

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 intended behavior is front-loaded in one sentence, followed by the kind vocabulary and a closing rationale for ordering. The kind list is dropped in without a lead-in phrase, which slightly hurts scannability, but there is no filler and every sentence adds information.

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 four-parameter mutation with no annotations and no output schema, the description covers the core action and the kind taxonomy but leaves the evidence object and the workflow_id reference unexplained, and it does not say what is returned on success. Adequate to attempt a call, not complete enough to call with confidence.

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% across four parameters, so the description must compensate. It does so for 'kind' by enumerating eight allowed values (observation, decision, action, verification, blocker, lesson, note, approval), which the schema leaves as a bare string with no enum. But it says nothing about 'text', 'evidence', or 'workflow_id', so half of the parameters remain undefined in both the schema and the description.

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 opening line gives a concrete verb and resource: 'Add one step to the workflow ledger.' That phrase distinguishes it from the sibling reporting/start tools (body_workflow_report, body_workflow_start), which read or create workflows rather than appending an entry. It stops short of naming a sibling explicitly, so it is clear rather than differentiating at the highest level.

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 does offer a real usage rule: write the decision before the action and the verification after it, so the run stays auditable. That is ordering guidance for how to use the tool, but it never says when to reach for this tool instead of a sibling such as memory_note or body_workflow_report, and it says nothing about preconditions, such as whether the workflow must already exist.

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