envelope_propose

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

Adds substantial behavior beyond annotations: the operation writes an 'envelope_proposed' ledger event and is attribution-gated, refusing if the orchestrator session lacks a keyring attribution. It also explicitly states that no force is applied until ratification, which is critical expected-effect information. No contradiction with readOnlyHint=false/destructiveHint=false.

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?

Two sentences, with the core action and constraints front-loaded and no filler. Every sentence contributes workflow, guardrail, or side-effect 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?

The description covers purpose, side effect, and guardrails, but with six parameters, zero schema descriptions, and no output schema, it leaves essential invocation details missing. An agent would struggle to know what a valid 'bounds' object or 'verb' value looks like or how expiry and max_count are used.

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?

With 0% schema description coverage, the description must carry parameter meaning, but it does not explain verb, grantee, bounds, reason, max_count, or expires_at. 'bounds' and 'verb' in particular are ambiguous, and the destination 'pre-approved.json#proposals[]' does not clarify them. The description offers no parameter-level guidance, so an agent cannot reliably construct arguments.

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?

States a specific verb ('Draft') and resource ('an envelope into pre-approved.json#proposals[]'), immediately distinguishing this as the proposal-stage tool. The phrase 'No force until the operator ratifies' differentiates it from sibling tools like envelope_apply and envelope_ratify.

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?

Describes the intended workflow position: draft proposals that cannot take effect until operator ratification, which tells an agent when to choose this over force/ratify tools. It also names a precondition (session must be keyring-attributed, PR1-4). It stops short of explicitly naming sibling alternatives and when not to use it.

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