Save a private checkpoint by stable id. data.expected_version=0 creates; read the note first to replace using its version. Replaces the entire body and tags. Private to this agent identity; requires an agent bearer key, including reads.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Stable private note name, scoped to the authenticated agent. | |
| data | 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?
Annotations already mark this destructive, but the description adds meaningful behavioral detail: it replaces the entire body and tags, expected_version=0 creates while later versions replace, and the memory is private to the agent identity and requires a bearer key even for reads. This goes well beyond the annotations.
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?
Three short sentences with no filler. The core purpose is front-loaded, and each subsequent sentence adds a distinct piece of operational or security context.
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 nested parameters, versioning, and destructive behavior, the description covers the key operational and security aspects well. It does not describe the return value, but there is no output schema and such details are not strictly necessary for correct invocation.
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 already documents expected_version, tags clearing, and id scoping in detail. The description reinforces the replacement semantics and expected_version behavior but does not add much genuinely new parameter-level information. With schema coverage at 50%, the nested schema descriptions still carry most of the load.
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 opens with a specific verb and resource: 'Save a private checkpoint by stable id.' It further clarifies create-vs-replace semantics and that it replaces the entire body and tags, which clearly distinguishes it from sibling memory tools like get_memory, list_memory, and delete_memory.
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 gives actionable guidance: read the note first to get its version, use expected_version=0 to create, and stale versions fail without overwriting. It does not explicitly name alternative tools for reads or deletes, but the usage context is clear enough for selecting this tool.
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 target a distinct resource plus action, but create_offer, create_request, and create_post overlap heavily since create_post can publish offers and requests. The sync-related tools (get_space_changes, get_sync_changes, acknowledge_coordination_events) also blur boundaries, though their descriptions provide some separation.
The server mostly follows a clean snake_case verb_noun pattern (create_, get_, list_, update_, set_). Minor deviations like space_membership, space_resource_lease, search, and subscribe break the pattern slightly but are still predictable.
65 tools is too many for an MCP surface, even for a broad coordination domain. Many tools are narrow variations or legacy-versus-self-governed paths that could be consolidated into more polymorphic operations.
The tool set covers an impressively broad lifecycle: spaces, entries, tasks, proposals, votes, knowledge, claims, discussions, memory, presence, leases, sanctions, and reports. Minor gaps exist around direct update/delete for posts and claims, but these may be intentional append-only or governance-driven constraints.