Optional private preferences and collection. Read/export or delete your data; saving requires consent. Sharing a collection item requires publish_consent and founder moderation. Never upload secrets. No model memory writes.
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| action | Yes | ||
| item_id | No | ||
| account_ref | No | Native connector: persistent individual-agent scope. Reuse the same reference on every call; omit to use the existing default account. |
Changes observed during successful MCP inspections.
Input schema / properties / account_refAdded value: +{
+ "description": "Native connector: persistent individual-agent scope. Reuse the same reference on every call; omit to use the existing default account.",
+ "maxLength": 80,
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=true, so the destructive surface is partly covered. The description adds real context beyond that: consent gating on save, moderation gating on share, 'Never upload secrets', and 'No model memory writes'. However it never says which of the nine actions are irreversible or what deletion actually destroys, so the disclosure stays partial.
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 short and packs several rules, but it reads as telegraphic fragments rather than a front-loaded statement of purpose, and the opening sentence ('Optional private preferences and collection') is ambiguous about what the tool actually is.
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?
This is a complex tool: four parameters, a nine-value action enum, a nested object, no output schema, and only 25% schema coverage. The description leaves action semantics, return values, and per-action behavior undocumented, so it is not complete enough 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?
Schema description coverage is only 25% and the description explains none of the four parameters. The nine-value action enum (read_preferences, save_item, gallery, pilot, etc.) is completely unexplained, and the untyped 'data' object is not characterized, so the description does not compensate for the coverage 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 names a domain (private preferences and a collection) and lists capabilities (read/export/delete, save, share), but never states the tool's operation in verb+resource form and never distinguishes it from nearby siblings like eclypse_agent_profile, eclypse_approved_memory, or eclypse_memory_workspace. An agent can guess the domain but not the boundary of this tool.
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?
It states prerequisites ('saving requires consent', sharing 'requires publish_consent and founder moderation') but gives no when-to-use guidance and names no alternative. With nine sibling eclypse_* tools and no routing signal, the agent gets conditions without direction.
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.