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

With no annotations provided, the description carries the full behavioral burden. It does disclose a key non-mutating guarantee: 'Even unanimous reviews never mutate duplicate_of or supersession edges.' It also labels the review as 'advisory,' implying it is non-authoritative. However, it does not describe other behaviors such as idempotency effects, failure modes, or persistence details, leaving gaps.

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 concise, with two sentences and no redundant filler. The conditional requirement and behavioral guarantee are front-loaded before the second sentence. The only minor issue is the leading 'AUTH:' prefix, which is unexplained and could confuse agents, but overall it is structurally efficient.

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?

Given the tool has 6 parameters (5 required) and one conditional, no annotations, and no output schema, the description is insufficiently complete. It does not explain the core parameters, the meaning of the decision values, what 'surface-bound' and 'advisory' imply for system state, or how idempotency is handled. An agent would struggle to construct a valid call without further documentation.

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 for parameter meaning. It only clarifies that 'expected_predecessor also requires predecessor_slug,' which is a conditional dependency. It does not explain left_slug, right_slug, reason, decision enum values (beyond the name being self-explanatory), or idempotency_key. The description provides minimal additional meaning for most parameters, failing to compensate for the schema's lack of descriptions.

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 a specific action: 'append a surface-bound advisory review of one current lexical candidate pair.' This includes a concrete resource (lexical candidate pair) and distinguishes it from read tools like get_semantic_reviews. It is not a tautology and immediately conveys the write nature of the tool.

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 implies when to use the tool (to add a review) but does not explicitly contrast it with alternatives such as get_semantic_reviews or other proposal tools. The mention of the conditional predecessor_slug requirement provides some usage context, but there is no explicit 'use this instead of X' guidance, leaving some inference to the agent.

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