How Good It Can Get™ Clarity OS

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

With no annotations, the description carries the full burden and does substantial work: it discloses the tool is nonclinical, governed, preserves uncertainty and personal agency, and may return protective safety routing. It does not address data handling, latency, or whether the person's text is stored, which for a sensitive mental-health-adjacent tool is a residual gap.

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?

The trigger conditions are front-loaded in the first sentence, followed by capability, then the exclusion list. It is appropriately sized for the tool's complexity, with only mild redundancy between 'identify what is happening, clarify what matters, and choose a grounded next step' and the surrounding framing.

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 8-parameter tool with nested objects and no output schema, the description covers the primary input (`user_text`) and one output behavior (safety routing), but says nothing about the shape of the main clarity response or how the structured safety/capacity objects are used. It is adequate but leaves meaningful gaps for a safety-sensitive tool.

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 baseline is 3. The description only points at `user_text` ('Provide the person's situation in `user_text`') and adds nothing about the optional structured parameters like `safety_evidence`, `capacity_signals`, or `requested_resource`, leaving the schema to do all the work.

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 states a specific function (governed, nonclinical clarity support) and enumerates the triggering situations it handles: overthinking, emotional activation, uncertainty, decision friction, repeating patterns, difficult conversations. It is clear what the tool does, though the abstract phrasing ('clarity support') leaves the concrete output somewhat fuzzy; no siblings exist to differentiate against.

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-to-use is given as a concrete list of presenting problems, and when-not-to-use is stated directly: 'Do not use for diagnosis, treatment, crisis intervention, or emergency support.' With no sibling tools, no alternative routing is needed, so the guidance is complete.

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