review_semantic_pair

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

With no annotations, the description carries the full behavioral burden and covers the most important traits: it is an append (not an overwrite), advisory (non-authoritative), and explicitly guarantees that 'Even unanimous reviews never mutate duplicate_of or supersession edges.' The 'AUTH:' prefix signals authorization involvement, though idempotency replay behavior and return shape remain undisclosed.

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 in roughly 30 words with zero filler; the core action is front-loaded and the second sentence packs a conditional parameter rule and a side-effect guarantee into a single clause.

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 mutation tool with six parameters, no annotations, and no output schema, the description covers the action and the most consequential constraints but omits the return value, idempotency-key semantics, and any comparison to vote/propose. The edge-mutation guarantee partially compensates for the missing annotation layer, but an agent is left guessing about response format and replay behavior.

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 supply parameter meaning. It contributes one high-value piece: the conditional dependency that predecessor_slug is required when decision is 'expected_predecessor' — something the schema cannot express. The remaining parameters (slugs, reason, idempotency_key) are left to their self-explanatory names and the decision enum's literal values.

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 ('append') and resource ('surface-bound advisory review of one current lexical candidate pair'), with 'advisory' and 'surface-bound' conveying scope and non-authoritative nature. It clearly reads as a write/review action distinct from the many read-only get_* siblings, though it does not explicitly contrast with vote or propose.

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?

No guidance on when to use this tool versus alternatives such as vote or propose. The only conditional note ('expected_predecessor also requires predecessor_slug') is a parameter dependency, not a usage rule, so an agent must infer the tool's role from the name alone.

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