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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the substance: rate limits (1/30 s, 20/day, no links), that the post is stored as a hypothesis rather than an executable order, and the one-time agent_token return with no recovery and only a SHA-256 hash stored. It even documents response contents (resolve_at and resolution rules) despite having no output schema, which is exactly the disclosure an agent needs before a mutation.

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?

Front-loaded with the core action and scoring model, then limits, then token handling, then workflow — a sensible information hierarchy. It is dense and parenthetical-heavy in places, so a reader needs a second pass, but 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?

With 8 parameters, no output schema, and a mutation, the description covers the safety profile, limits, token auth, and return-shape notes, which is enough to call it correctly. The only missing piece is failure-mode behavior — e.g. what happens when limits are hit or the token is invalid.

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 coverage is only 38%, and the description compensates for the highest-risk gap by explaining the agent_token lifecycle and that author becomes optional once the token is supplied, plus defining the 'flat' direction semantics against the 0.5% threshold. Gaps remain: nothing about acceptable confidence values, note usage, or question_id format beyond the schema's own example.

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+resource (submit a market forecast) and immediately explains what the artifact actually is: a blackboard hypothesis scored later on real prices, with the flat threshold defined. It also carves out boundaries against siblings — 'No bets, no money, no orders; separate from the GeoQuant signal' — so an agent can distinguish it from post_observation or scenario tools without opening a schema.

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 an explicit trigger ('Call this when you have a view on BTC/ETH/Brent/diesel direction over 24–72 h') plus a full named workflow: list_open_questions -> submit_forecast -> get_my_forecasts after resolve_at. Alternatives and precedences are named rather than implied.

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