envelope_apply

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

With no annotations, the description takes on full responsibility for disclosing side effects and edge cases. It states that the tool appends a citation, refuses with a reason for missing/expired/out-of-scope grants, and explicitly explains the double-charging workaround for dispatch verbs, including that `cited_before_act` returns False and no citation is written. This is exceptional transparency.

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 front-loaded with the core purpose in the first sentence, and the #333 note provides essential operational detail in a structured way. While the note is long, every sentence adds necessary information about edge-case behavior, making it appropriately sized for the tool's complexity.

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 6-parameter tool with no annotations or output schema, the description covers the main flow, error handling, and the notable dispatch exception. It lacks an explicit statement of return values for the normal path, and app_id remains unexplained, but overall it is nearly complete and leaves few critical gaps.

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?

The schema provides only parameter names with no descriptions, so the description must explain their meaning. It does: envelope_id, verb, call_args, project, and session are all contextualized within the verification and citation flow. However, app_id is never mentioned, leaving one of the six parameters underspecified despite the low schema coverage.

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 tool's function: checking an authority envelope before acting under it, verifying the envelope is active and covers the verb/call_args, and appending a FRANK ledger citation. It distinguishes itself from sibling tools by framing the operation as a pre-action check-and-cite flow, and names the specific resource (authority envelope).

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 says to use this tool BEFORE acting under an envelope, and provides a clear when-not-to-use case for dispatch verbs, where it is advisory-only and the verb handler (dispatch_send) is authoritative. It names this alternative handler, though it does not enumerate other alternatives for non-dispatch verbs.

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