Verdict per post (refresh / expand / merge / kill / double_down / hold)

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

Annotations already declare readOnlyHint=true, destructiveHint=false, so safety is covered; the description usefully adds that reason codes are deterministic, that the verdict carries a 0-1 confidence, and that it performs no mutation. It does not clarify the tension between the 'does NOT mutate' claim and the schema's 'persist' flag, nor the non-idempotent hint.

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?

Front-loaded with the operation, then behavior, then the routing alternative in three tight sentences. The pointer to src/verdict/rules.ts is a minor implementation detail that slightly dilutes an otherwise efficient block.

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?

An output schema exists, so return values need not be described, and the description is adequate on purpose and safety. But two of three parameters (window, persist) remain unexplained, and the persist flag sits awkwardly against the 'reporting only' framing, leaving an agent with real gaps before invocation.

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 only 33% — url is documented, but 'window' (30/60/90) and 'persist' are bare. The description never explains what window means (trailing days?) or what persist=true does, which is especially important given the explicit 'does NOT mutate anything' claim.

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 and resource ('Run the rule-based verdict engine on a single post') and names the exact inputs it combines (snapshot + decay curve) and outputs (verdict, reason codes, 0-1 confidence). The 'single post' scope also differentiates it from list-oriented siblings such as posts_list.

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?

Gives clear context (per-post verdict after snapshot and decay data exist) and an explicit when-not: it is reporting only, and acting on the verdict is routed to a writer or AI rewrite tool. It does not, however, say when to prefer this over sibling read tools like posts_snapshot or posts_decay_curve.

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