envelope_apply

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

The description discloses all side effects: it verifies and then appends a citation. It explicitly states that for dispatch verbs it does NOT write a citation and returns cited_before_act=False with a note. It explains refusal behavior (returns reason if missing/expired/out of scope). This far exceeds what annotations provide (annotations only indicate non-read-only, non-destructive) and adds crucial nuance about the double-charging issue.

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 lengthy and contains a dense technical note about double-charging. While the main purpose is front-loaded in the first sentence, the #333 note is a large block of text that could be structured more clearly (e.g., bullet points). It is not overly verbose for the complexity, but it is not concise; a structured breakdown would improve scannability.

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?

The description covers the main functionality, the special handling for dispatch verbs, and failure behavior. It hints at the return structure (cited_before_act, note) but does not fully specify the output format or all possible error types. For a tool with no output schema, this is a reasonable level of detail; it provides enough to call the tool correctly, though a return format specification would make it more complete.

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%, so the description must compensate. It explains the roles of envelope_id, verb, call_args, project, and session (they are used for verification and citation recording). However, app_id is not explained at all, and call_args is only vaguely described as 'given call_args' without structure. While most parameters are given meaning, the gap on app_id prevents a higher score; a 4 is appropriate given 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: it checks an authority envelope before acting, verifies the envelope covers the verb and arguments, and appends a citation to the FRANK ledger. It also introduces the advisory-only distinction for certain verbs, which separates it from generic append tools like frank_append. The verb+resource is specific and unambiguous.

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?

Explicitly states when to use the tool: 'BEFORE acting under it.' It clearly explains the exceptional case for VERB_LEVEL_ENFORCED_VERBS (dispatch) where the tool becomes advisory-only and cites are handled by dispatch_send, preventing double-charging. This gives strong guidance on when to rely on it and when not to, including practical use for preflight checks.

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