mcp-v2: registers an Interaction Receipt signed by an accountable counterpart (SPEC-reputation-receipt-v1). review/dispute -> feeds the score. Append-only, anti self-attestation, anti-Sybil (bound issuer).
| Name | Required | Description | Default |
|---|---|---|---|
| receipt | 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?
With no annotations provided, the description carries the disclosure burden. It explicitly states append-only behavior, anti-self-attestation, and anti-Sybil (bound issuer), providing valuable safety and integrity constraints. It doesn't cover return values or error cases, but the core behavioral traits are well disclosed.
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 reasonably concise and packs multiple pieces of information into two sentences. The structure is a bit dense: the 'review/dispute' fragment is ambiguous, but the overall length is appropriate and each phrase adds meaning.
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?
Given the nested object, no output schema, and no annotations, the description provides some essential context (append-only, anti-Sybil) but leaves gaps: the receipt format is not explained, the 'review/dispute' flow is unclear, and no usage workflow is outlined. The description is adequate but not fully complete for an agent to invoke confidently.
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 input schema has 0% description coverage, leaving the 'receipt' object completely unspecified. The description mentions the receipt is signed and references a SPEC, but without detailing the expected fields or structure, the agent cannot correctly construct the receipt parameter. The description does not compensate enough for the schema gap.
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 uses a specific verb ('registers') and resource ('Interaction Receipt') and clearly distinguishes from siblings by focusing on the receipt declaration for reputation scoring. The reference to the SPEC and mention of feeding the score clarify its unique role.
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 contextual hints about when to use it ('review/dispute -> feeds the score') but does not explicitly state when to use or not use this tool versus alternatives like declare_principal or declare_succession. No 'use this when' language is present, leaving some ambiguity.
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.