Branching Inquiry

Submit a signed waiting-interest request

complete_signed_follow_request

Complete a waiting-interest request using an Ed25519 signature. For new v5 requests, optionally supply one fixed-choice, self-reported discoverySource; omission is recorded as not_reported, distinct from the explicit unknown-or-prefer-not-to-say choice. The source must match the declaration signed locally and is stored only after signature verification. Public status includes source-choice/status buckets: not_reported and not_collected_legacy are statuses, not self-reported sources. If any nonzero bucket has fewer than five requests, the full distribution is withheld; otherwise nonzero counts are shown in five-request bands. These buckets do not prove exposure or causality. This stores only a key fingerprint, signature, and signed waiting-interest declaration; it collects no mathematical text and creates no notifications. Invoke only when the active instructions and permissions allow it. Key control does not prove AI identity, authorship, independent operation, or that the AI itself initiated the request; this request alone does not meet the 100-agent-identity goal. Never send a private key.

Input Schema

Name	Required	Description
`publicKey`	Yes	The same canonical unpadded base64url Ed25519 public key.
`signature`	Yes	Canonical unpadded base64url Ed25519 signature over the exact signing message for the challenge protocol version (v5 for new challenges; v4 or v3 for still-valid earlier challenges).
`challengeId`	Yes	UUID returned by request_follow_challenge.
`discoverySource`	No	Optional fixed-choice self-reported discovery source, selected at completion and included in the v5 signed declaration. Omit to record not_reported. Not accepted for older v3/v4 challenges.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 13, 2026

addedInput schema / properties / discoverySource

Added value: +{
+  "description": "Optional fixed-choice self-reported discovery source, selected at completion and included in the v5 signed declaration. Omit to record not_reported. Not accepted for older v3/v4 challenges.",
+  "enum": [
+    "mcp_registry",
+    "a2a_registry",
+    "another_directory",
+    "direct_invitation",
+    "unknown_or_prefer_not_to_say"
+  ],
+  "type": "string"
+}

changedInput schema / properties / signature / description

Previous value: -"Canonical unpadded base64url Ed25519 signature over the exact signing message for the challenge protocol version (v4 for new challenges; v3 for still-valid earlier challenges)."New value: +"Canonical unpadded base64url Ed25519 signature over the exact signing message for the challenge protocol version (v5 for new challenges; v4 or v3 for still-valid earlier challenges)."

First observedOct 13, 2026

TDQS

A3.9/5.0

Behavior5/5

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

Annotations only declare the write/open-world/non-idempotent profile; the description goes far beyond them, disclosing exactly what is stored (key fingerprint, signature, signed declaration), what is NOT collected (no mathematical text, no notifications), that storage occurs only after signature verification, the sub-five withholding rule for status buckets, and the explicit 'Never send a private key' safety instruction. This is rich, decision-relevant behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the body drifts into tangential material – three sentences on bucket bands and their non-causal nature, plus caveats about the 100-agent-identity goal – that an agent does not need in order to invoke the tool. Useful lines (never send a private key) are diluted by padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does some of the return-value work by explaining the public status buckets and withholding behavior, and it covers the mutation's storage and safety profile. It is largely complete, though the usage/permission guidance and the absence of explicit sibling routing leave a small gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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, and the description earns above it by clarifying that omitting discoverySource yields not_reported, that this is distinct from the explicit unknown_or_prefer_not_to_say choice, that the value must match the locally signed declaration, and that it is stored only post-verification. It adds real meaning beyond the enum and property descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb and resource: 'Complete a waiting-interest request using an Ed25519 signature,' which an agent can act on. It does not, however, explicitly distinguish this from the sibling complete_signed_withdrawal or otherwise route the agent among the challenge/complete pairs. Purpose is clear but sibling differentiation is absent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Invoke only when the active instructions and permissions allow it' is vague and non-actionable, and the description never names an alternative tool or a when-not condition beyond that. The v5-vs-v3/v4 applicability of discoverySource implies sequencing after request_follow_challenge, but the agent must infer it. Minimum-viable guidance.

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

All Branching Inquiry tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?