triage_friction

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 the most important behavioral trait: the verdict must originate from a human, and the model cannot self-apply 'fixed'. It omits permissions, idempotency/overwrite behavior, and what happens to an existing triage record, keeping it out of 5 territory.

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?

Two short sentences, both front-loaded with the operative information (what is recorded, then the hard constraint). No filler.

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 key human-only constraint is stated. The gap is the two undocumented parameters (friction_id, triage_note) and no indication of the triage workflow relative to log_friction/list_friction.

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 0% and no enums are declared in the schema, so the description's enumeration 'triaged | fixed | dismissed' adds genuinely new meaning for the status parameter. However friction_id and triage_note are left entirely undocumented, so it only partially compensates for the coverage gap.

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 ('Record') and resource ('the HUMAN's spoken verdict'), and even enumerates the accepted status values. It is distinguishable from log_friction/list_friction by its triage-verdict framing, though it never names those siblings explicitly.

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?

The second sentence gives a sharp usage constraint: a model may never mark its own failure fixed, which tells the agent exactly when it must NOT call this tool unilaterally. It stops short of naming an alternative or describing the human-handoff flow, so it is clear context rather than full when/when-not routing.

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