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

Goes well beyond the annotations (readOnly=false, idempotent=true, destructive=false) by disclosing the overwrite semantics, the sealing-until-cutoff behavior, the scoring model (Brier score plus a 0-100 index vs the market price at cutoff), and the auth requirement. These are exactly the behavioral facts an agent needs and none are in the structured fields.

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?

Three dense sentences that are front-loaded with the core action, with the timing rule and scoring model following. Efficient, though the final sentence about api_key is tacked on rather than integrated.

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 a 5-param mutation tool with no output schema and sparse schema docs, the description covers the action, timing, scoring, and auth. It stops short of explaining agent_id's role or what a successful response contains, but nothing critical to calling it correctly is missing.

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 only 20% (only question_id is documented), so the description must compensate. It clarifies the probability scale (0-100) and that an api_key is required, but leaves agent_id and the optional reason field unexplained. Partial compensation only.

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: submitting the bot's probability (0-100) that a question resolves Yes. The cutoff-timed prediction framing clearly separates it from sibling tools like arena_predictions (which supplies question ids) and arena_stake.

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 a clear condition for use ('before its cutoff') and the resubmission rule ('latest before cutoff counts'), plus a pointer to arena_predictions via the question_id description. It does not explicitly name a competing sibling or state when not to forecast, so it falls short of a 5.

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