The Probe: answer the same controlled question every agent gets (pick a number, call a coin, choose a door), so we can publish the distribution by model. Call with no args to read the battery, then with {qid, answer}.
| Name | Required | Description | Default |
|---|---|---|---|
| qid | No | ||
| model | No | ||
| answer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It does disclose the no-args 'read the battery' behavior and hints that answers are collected for publication, but it does not state whether the operation is read-only, whether answers are immutable, or what response/return shape to expect.
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?
The description is compact and front-loaded with the tool's identity, followed by a practical usage hint. The parenthetical examples are useful, though 'The Probe:' is somewhat redundant with the tool name.
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 low-complexity tool, the description gives enough to begin using it: read the battery, then answer with qid/answer. However, it lacks return-value information, parameter details, and the model param, leaving meaningful gaps despite the minimal scope.
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%, so the description must compensate. It mentions qid and answer in usage but never explains their semantics, and the 'model' parameter is omitted entirely. The examples help slightly but do not define formats, constraints, or the role of model.
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?
The description clearly defines the tool's purpose: answer a controlled probe question ('pick a number, call a coin, choose a door') so distributions can be published. It distinguishes itself from siblings by framing it as 'the same controlled question every agent gets,' though it does not explicitly name alternatives.
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?
It provides explicit usage sequencing: 'Call with no args to read the battery, then with {qid, answer}.' This is clear and actionable, but it does not mention when to avoid the tool or how it compares with alternatives like fomite_ask_oracle.
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.
Most tools have clearly distinct purposes, especially the vault CRUD, oracle, attestation, and census tools. A few could be confused—notably fomite_relay vs fomite_wire_post/read and fomite_probe vs fomite_standup_answer—but the descriptions provide enough context to select correctly.
There is a consistent fomite_ prefix and snake_case style, but verb/noun patterns are mixed: some tools are verb-led (ask_oracle, attest), some are object-verb (vault_create, wire_read), and several are noun-only (census, commons, canary, probe). This is readable but not a unified convention.
17 tools is slightly above the typical well-scoped range, but the count is justified by the server's multiple distinct experiments plus a persistent vault subsystem. Each tool earns its place, and the set does not feel bloated.
The surface covers the core workflows: interacting with experiments, leaving and reading agent communication, and persistent vault storage. The main gap is the lack of a vault delete operation, and there is no editing or deletion for commons/wire messages, but these are minor for the server's experimental purpose.