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

With no annotations, the description carries the full burden and does disclose real behavior: it proposes but never confirms ('no verdict, no seal'), holds back private/framing context ('not sent'), routes crisis cases, and generates nothing. The privacy disclosure (private context not sent) is a genuinely valuable trait beyond the schema. It omits rate limits, auth, or return-shape specifics, keeping it at 4.

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?

It is front-loaded with the core function, but the metaphorical framing ('WALK · door', 'proposal half of the engine, laid open') and a redundant close ('It PROPOSES, never confirms' / 'no verdict, no seal' / 'nothing is generated') inflate a one-parameter tool's description. Information density is high, but several clauses do not earn their place.

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?

There is no output schema, so the description must explain returns — and it does, enumerating KIND, the reduced claim, the (domain, spec), and routing, plus the handoff to verify. For a single-input tool this is largely complete, though return format/structure detail is left somewhat abstract.

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% and there is only one parameter ('text', maxLength 4000), so the schema already documents it. The description restates the same semantics ('a claim, a question, or a messy statement') without adding format or constraint detail. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

It states a specific verb (discern) and describes the concrete transformation: take a claim/question/messy statement, return its KIND, the reduced necessary claim, the (domain, spec) the gate would verify, and where it routes. It also explicitly distinguishes itself from its sibling ('The twin of the verify door', 'It PROPOSES, never confirms'). The heavy metaphor ('WALK · door', 'proposal half of the engine') adds fog, but the functional identity is recoverable.

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?

It names the alternative and the handoff condition explicitly: 'hand the returned `claims` to `verify` to dispose', plus the crisis routing rule ('routed to real people, never the gate'). This gives a clear workflow and selection boundary versus verify. It stops short of stating when NOT to call discern (e.g., when a verdict is already wanted), so it is not a full 5.

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