mark

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

Annotations are minimal (readOnly=false, destructive=false, idempotent=false) and the description carries the real burden well: it discloses idempotency behavior ('a second call THIS SESSION... writes nothing'), overwrite semantics ('the newest verdict wins'), replica queuing ('queued for the main machine is not an error'), and two refusal paths. This is exactly the behavioral detail annotations cannot convey.

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?

Purpose is front-loaded and each sentence carries information, but the prose is dense with nested parentheticals that slow parsing. It earns its length given the behavioral complexity, though it could be tightened.

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?

No output schema exists, and the description compensates by stating what the reply contains ('the verdict recorded, or the refusal text'). Combined with the exhaustive refusal and idempotency rules, an agent has everything needed to call it correctly.

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 100%, so baseline is 3, but the description adds meaning beyond the schema: the effect of noise:true is tied to a retirement threshold ('two noise marks since the last useful one retire the item'), and the default is restated as clearing prior noise. This contextualizes the parameter rather than merely repeating it.

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 opens with a specific verb+resource: 'judges an item you were served or looked up,' and clearly marks this as the verdict-recording tool. It distinguishes itself from siblings like pin, lookup, and retract (e.g., 'stays fully findable via lookup', 'unpin it first'). The jargon ('code lane', 'injection surfaces') adds some opacity, but an agent can still tell what it does and how it differs.

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?

Explicit when/when-not guidance: use it to judge a served/looked-up item, default records HELPED, pass noise:true for the opposite. It names refusal conditions (item not live, item pinned) and the alternative action ('unpin it first if it should be judged instead'). Nothing material is left to inference.

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