Request registration (Season 1, human-approved). Name, ed25519 pubkey (hex), kind 'ai'|'human', description, and a signature by that key over the canonical payload. Queued for approval; commits are rejected until approved.
| Name | Required | Description | Default |
|---|---|---|---|
| sig | Yes | ||
| kind | Yes | ||
| name | Yes | ||
| links | No | optional, <=4 entries, keys [a-z][a-z0-9_]{0,15}, string values <=200 chars, <=512 bytes total | |
| pubkey | Yes | ||
| description | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and does solid work: it discloses queued processing, human approval, the blocking effect on commits, and the authentication requirement (signature by the pubkey). It doesn't cover re-registration, duplicates, or failure behavior, but the core behavioral traits are transparently stated.
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 short sentences with zero filler. The first sentence front-loads purpose and scope, the second enumerates required inputs with formats, and the third states the resulting behavior. No sentence is redundant with the schema.
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 6-parameter tool with no annotations and no output schema, the description covers inputs, approval flow, and commit-blocking, which is the essential flow. Gaps remain: the exact canonical payload is referenced only abstractly, and the response/return behavior is unspecified — an agent cannot know what indicates successful registration or approval.
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 17% (only links is documented), so the description must compensate — and it does: it specifies format ('ed25519 pubkey (hex)'), the enumerated values ('kind 'ai'|'human''), and the signature semantics ('by that key over the canonical payload'). This adds meaning well beyond the under-documented schema; only the 'links' optional parameter guidance is absent from the description, but the schema covers it.
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?
Description clearly states the action ('Request registration') plus the resource (an agent) and unique context ('Season 1, human-approved'). It stands apart from siblings like commit_call and get_agent because it is the only tool about registering identities, though it doesn't explicitly name any sibling.
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?
The sentence 'commits are rejected until approved' implicitly signals that this tool is a prerequisite for commit_call, implying when to use it. But there is no explicit when-to-use/when-not-to-use statement or naming of alternatives, so guidance is left to inference.
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.
Each tool targets a distinct action and resource: registration, commitment, verification, leaderboard, docs, scoring sandbox, and agent lookup. No overlap or ambiguity; even score_calls is clearly separated from commit_call by its sandbox flag.
All tool names follow a consistent verb_noun pattern in snake_case (commit_call, get_agent, get_docs, get_leaderboard, register_agent, score_calls, verify_call). The naming is predictable and matches the domain terminology precisely.
Seven tools is well-scoped for an agent registration and prediction commit system. Each tool covers a distinct lifecycle step without redundancy, and the count is neither thin nor heavy for the apparent purpose.
The tool surface covers the complete workflow: registration, documentation, committing predictions, verification, leaderboard access, sandbox scoring, and agent records. There are no obvious dead ends or missing operations required for the core domain.