How Good It Can Get™ Clarity OS

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

Annotations already establish readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: it is nonclinical and governed, it preserves uncertainty and personal agency, and it may return protective safety routing. It does not describe the shape of a normal response, but the safety-relevant behavioral context is unusually well disclosed.

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?

Four sentences, front-loaded with the use case and followed by capability, exclusions, and the single required input instruction. Every sentence carries information (scope, behavior, prohibitions, input), though the capability sentence is somewhat long and 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?

For an eight-parameter tool with nested objects and no output schema, the description covers domain, exclusions, and the required input. The unenumerated nested objects (safety_evidence, capacity_signals) are only loosely described in the schema, but that is a schema defect rather than a description gap. Output content is only lightly implied ('choose a grounded next step', 'protective safety routing'), which is the main remaining gap.

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 100%, so the schema already documents all eight parameters, including the 'omit rather than guess' guidance on optional fields. The description adds only one parameter-level instruction, 'Provide the person's situation in user_text,' which restates the required field without adding format or content guidance beyond the schema. Baseline 3 is appropriate where 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?

The description names the trigger conditions concretely (overthinking, emotional activation, uncertainty, decision friction, conflicting priorities, repeating patterns, difficult conversations) and states the outcome-oriented job: identify what is happening, clarify what matters, and choose a grounded next step. The verb/resource pairing is somewhat abstract ('governed clarity support'), so it is clear but not as crisp as a named operation on a named resource. With no siblings, no sibling differentiation is needed.

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 gives explicit when-to-use criteria and an explicit when-not-to-use list: 'Do not use for diagnosis, treatment, crisis intervention, or emergency support.' It also signals a routing behavior ('may return protective safety routing'), which tells the agent how the tool behaves at the boundary of its scope. There are no alternatives to distinguish from, so nothing further is required.

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