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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the description must add beyond that. It does contribute real context: the result is a pending card requiring human review, retry identity is the exact client_id plus unchanged body, and acceptance is gated on the canonical controller or confirmed phone. What is missing is the destructive side — it never says what the card supersedes or what replaces_decision_id destroys/replaces, leaving the destructiveHint unexplained.

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?

Three dense sentences with no filler, and the core operation is front-loaded before the retry and authorization details. The density of unstated domain terms (Brief, card, controller) costs a point against perfect clarity, but nothing is redundant.

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 destructive, open-world mutation with seven parameters and no output schema, the definition covers prerequisites, idempotency, and authorization but omits the lifecycle: what a pending card becomes after acceptance or rejection, and the effect of replacing an existing decision. Those gaps matter for calling the tool correctly in sequence.

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 57%, so the schema does part of the work, and the description genuinely clarifies message_number (must be the assistant's own saved number), base_revision (must be the current Brief revision), and client_id retry semantics. However, supports_action_id and replaces_decision_id are left entirely unexplained, and their schema text is identical generic UUID boilerplate shared with client_id, so an agent cannot infer their meaning from either source.

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 states a specific verb and resource ('Creates a pending human-review card') and adds the binding constraints (own saved message_number, current Brief base_revision), so an agent knows the operation precisely. It does not, however, distinguish itself from the many similar siblings such as propose_decision, propose_relay_decision, or purpose_propose_decision, so the reader cannot tell from the text which proposal tool to pick.

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?

Usage is implied rather than stated: the agent learns it must hold its own saved message_number and a current Brief base_revision, and that acceptance needs the canonical human controller or confirmed phone. There is no explicit when-to-use versus alternatives, no when-not-to-use, and no named sibling to route to instead.

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