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

With no annotations, the description carries the full burden and does well: it discloses the return shape (selected label plus per-option probabilities), the accuracy caveat ('Model-estimated probabilities can be wrong'), an auth requirement ('funded account token') and a cost model ('charges input tokens'). Not disclosed are rate limits, determinism, or failure behavior, keeping it short of a 5.

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?

Roughly four dense sentences: purpose and use cases first, then input expectations, then return value, then caveats and cost. Nothing is redundant and no sentence is 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?

Only two required parameters and no output schema, so the description must explain the return value — which it does explicitly. Input constraints, cost, and reliability caveats are all covered; an agent has everything needed to invoke 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 description coverage is 100%, so both parameters are already fully documented in the schema, including the 2–20 / 80-character bounds that the description repeats. The only added semantic value is the advisory about including an unclear/escalate label. Baseline 3 is appropriate.

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 and resource ('fast single-label classification or routing') and backs it with concrete application examples (ticket triage, intent labels, tool selection). An agent immediately knows what the tool produces. It never explicitly contrasts itself with the sibling seb_decide / seb_batch_decide, so the single-label vs. multi-criteria distinction must be inferred.

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?

Gives rich when-to-use context through enumerated scenarios and practical setup advice ('add an unclear/escalate label if appropriate'). It also scopes what the tool will NOT do ('No explanation or downstream action'). It does not name an alternative tool or state when to prefer seb_decide over this one.

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