Verify a Progenly birth certificate (ed25519 attestation envelope). Pass a certificate object, or a birth_id for a public birth. Returns {ok, issuer_bound, reasons, notes}.
| Name | Required | Description | Default |
|---|---|---|---|
| birth_id | No | A public birth UUID to fetch + verify | |
| certificate | No | A full certificate envelope to verify |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It mentions the cryptographic type and return shape but does not disclose side effects (likely read-only), permission requirements, or error behaviors. The description is decent but could be more transparent.
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 extremely concise with two sentences. The first sentence states the purpose, and the second provides usage and return format. No wasted words.
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?
The description specifies the return structure ({ok, issuer_bound, reasons, notes}) despite lacking an output schema. It covers input modes and the core behavior. However, it omits details like error handling or field semantics, which would improve completeness.
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 100%, but the description adds value by clarifying that the two parameters are alternatives: either a certificate object or a birth_id for public births. This guides the agent on when to use each parameter beyond the schema's descriptions.
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 states the tool verifies a Progenly birth certificate with a specific cryptographic type (ed25519 attestation envelope). It distinguishes itself from siblings like 'get_certificate' (retrieval vs. verification) and specifies input options and return format.
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 description provides clear context on how to use the tool: pass a certificate object or a birth_id for a public birth. However, it does not explicitly state when not to use it or contrast with alternatives like 'verify_colony_handle'.
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 addresses a distinct operation: merge workflows (stage, join, lock, confirm, cancel, status) are separate from birth queries (get, list, search, random, certificate, lineage, verify) and auxiliary functions (stats, revocations, colony handle verification). No two tools have ambiguous purposes.
Most tools follow a clear verb_noun pattern (cancel_merge, get_birth, list_births), with minor exceptions like 'merge_status' (noun_verb) and 'random_birth' (adjective_noun). The convention is largely consistent and readable.
16 tools is a reasonable count for a system handling both birth certificates and merge intents. The number is well-scoped, not excessive, and each tool contributes to covering the domain without redundancy.
The tool surface covers the full merge lifecycle (stage, join, lock, confirm, cancel, status) and birth querying (get, list, search, random, certificate, lineage). While there is no explicit tool to create a birth (it is a product of a merge), the set feels complete for the intended workflows.
