Read the shared validated Pyth PriceUpdateV2 snapshot plus confidence, EMA, publish cadence, slots, observed feed health and the live Ratchet targets using each feed. Read this before ratchet_board when forming a probability. This call does not trigger a new oracle read.
| Name | Required | Description | Default |
|---|---|---|---|
| feed | No | Optional single feed; omit for all seven. | |
| hours | No | Observed health window in hours. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and adds an explicit behavioral guarantee: 'This call does not trigger a new oracle read.' It also characterizes the data as shared and validated, which helps the agent understand freshness and trust semantics. It does not describe return formatting or error behavior, but for a read-only context tool this is meaningful transparency.
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 sentences with no filler: the first front-loads what the tool reads, the second gives usage ordering and a behavioral caveat. Every clause earns its place.
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 read-only context snapshot with no output schema and no annotations, the description covers the data contents, the expected read-before-ratchet_board sequence, and the guarantee that no new oracle read is triggered. It omits return formatting and error conditions, but an agent has enough to decide when to call it and what to expect.
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 schema already documents the optional feed enum and the hours window with default, minimum, and maximum; the description adds no parameter-specific guidance. This is acceptable because the schema carries the meaning.
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 ('Read') and a precise resource: a shared validated Pyth PriceUpdateV2 snapshot plus confidence, EMA, publish cadence, slots, feed health, and Ratchet targets. This clearly distinguishes it from siblings like ratchet_board and ratchet_pyth_path, and the single declarative line captures exactly what the tool does.
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?
Explicitly instructs 'Read this before ratchet_board when forming a probability,' giving an actionable ordering relative to a known sibling. It does not spell out when not to use it or name all alternatives, but the intended context is clear enough for an agent to select it correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool targets a distinct resource or workflow: board, arena, Pyth context/path, proof, demo identity, ranked submission, invitations, and challenges. Even the many read-style tools are clearly separated by what they return, so an agent should not confuse them.
All tools use the ratchet_ prefix and snake_case, which makes them easy to group and predict. The pattern is not uniformly verb_noun—several tools are noun-style reads like ratchet_board and ratchet_arena—but the naming is still consistent and readable.
Thirteen tools is well within a reasonable scope for a forecasting arena. The tools cover context reads, demo workflows, ranked workflows, invitations, challenges, and public proofs without feeling padded or redundant.
The demo lifecycle is well covered with create, shoot, and state reads, and ranked prepare/submit gives a clear entry path. However, there is no ranked-state read to inspect open shots, balances, or settled results after submission, and challenges are read-only despite implying create/accept actions should exist.