claim_authorshipSubmit the signature from authorship_challenge. Proves you hold the key, upgrades the record to 'signed', re-signs its provenance manifest, and grants a founding seat if any remain. A record already signed by a different key is refused.
| Name | Required | Description | Default |
|---|---|---|---|
| did | Yes | ||
| model | No | Optional AI model to attest. | |
| nonce | Yes | ||
| signature_b64 | Yes | ||
| certificate_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
While annotations identify a write operation, the description goes further by explaining the actual mutation: it upgrades the record to 'signed', re-signs the provenance manifest, and may grant a founding seat. It also discloses an important refusal condition for records signed by another key. There is no annotation contradiction.
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, front-loaded with the action, and every sentence delivers useful information: what to submit, what happens as a side effect, and when the operation is refused. It contains no fluff or redundancy.
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 high-level workflow and side effects are communicated well, especially the provenance-manifest re-signature and founding-seat condition. However, with no output schema and five child children and multiple required parameters, the description could do a what the operation returns or clears about did/record identity. Still, the behavioral context is strong.
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?
The schema leaves 80% of properties undocumented, so the description must compensate. It links the username and nonce to 'signature' and 'authorship_challenge', but it does not explain did, certificate_id, nonce, or signature_b64 precisely. This is only marginal added meaning over the schema.
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 states a specific verb ('Submit') and a specific resource (the signature from authorship_challenge), then explains the resulting action: proving key ownership, upgrading the record to 'signed', re-signing the provenance manifest, and granting a founding seat. This clearly distinguishes the tool from its siblings by connecting it to authorship_challenge and the claimed record.
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 clearly places usage after authorship_challenge: you use this tool when you have a signature from that challenge and want to claim authorship. It also explains that a record already signed by another key is refused. It does not explicitly name alternatives or exclusions, but the flow is clear enough for a 4.
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 map to distinct workflows: certification, notarization, verification, prior art search, passport lookup, and council voting. The main ambiguity is between certify_creation and authorship_challenge, since both can produce a challenge to upgrade a record to 'signed', though their descriptions clarify different stages.
All names are lowercase snake_case and readable, but the pattern is mixed: half use a verb-noun form (certify_creation, notarize_hash, verify_certificate, get_agent_passport, claim_authorship) while the other half are noun-like (authorship_challenge, council_ballot, council_vote, legacy_testament, prior_art_search). This makes the naming less predictable than a fully consistent convention.
Ten tools is a well-scoped size for a server covering authorship certification, notarization, prior art search, agent identity, and council governance. Each tool addresses a distinct area of the domain without ballooning the surface.
The core certification, notarization, verification, search, passport, and voting workflows are present and connected. However, legacy_testament explicitly says it writes nothing, and there is no tool to actually seal or submit a testament, so an agent cannot complete that workflow through the MCP.