mcp-v2: registers a Principal Binding signed by the principal (SPEC-principal-binding-v1). Binds an agent to an accountable person/organization (did:key/did:web). Append-only, declarative, anti-Sybil.
| Name | Required | Description | Default |
|---|---|---|---|
| binding | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the burden. It adds behavioral traits such as 'Append-only' (no modifications/deletions), 'declarative' (likely idempotent), 'anti-Sybil' (purpose), and 'signed by the principal' (authentication). These go beyond the schema and provide useful 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, dense sentence that front-loads the core action ('registers a Principal Binding') and packs in spec version, purpose, and behavioral traits without wasted words. Every clause earns its place.
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 tool with one open object parameter and no output schema, the description gives a good high-level overview but leaves the binding parameter's structure underspecified. The agent would likely need additional documentation or examples to construct a valid binding. Thus, it is not fully complete.
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?
With 0% schema description coverage, the description should compensate. It hints at the binding content by mentioning 'agent', 'person/organization', and 'did:key/did:web', but does not specify the binding structure or required fields. Some semantic meaning is added, but it is insufficient for a fully open object parameter.
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 verb 'registers' and the resource 'Principal Binding', and further explains it binds an agent to an accountable person/organization. This distinguishes it from sibling tools like declare_receipt and declare_succession by specifying the exact binding type.
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 for when to use the tool: to register a Principal Binding and bind an agent to an accountable entity. It does not explicitly state exclusions or alternatives, but the context is unambiguous given the sibling tool names and the specific binding term.
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.
Tools are mostly distinct: declarations target different record types (principal, receipt, succession), and get/resolve have clear read purposes. However, 'register' and 'declare_principal' could be slightly confusing since both involve agent identity; descriptions clarify but overlap remains.
All names use lowercase with underscores, and three share the 'declare_' prefix. 'get_reputation' and 'resolve' are single verbs, but they follow a predictable verb-based style. Minor inconsistency from mixing 'declare_*' with standalone verbs.
Six tools is well within the sweet spot for an identity/reputation server. Each tool covers a distinct operation without redundancy, and the count feels neither thin nor bloated.
The surface covers core lifecycle: register agent, declare bindings/receipts/succession, get reputation, and resolve DIDs. Missing explicit queries for individual declarations, but the append-only design and aggregated reputation VC mitigate the gap.