Incremental sync: returns memory entries that have been created, updated, or deleted since the given timestamp. Scoped to namespaces your handle has explicitly written to (privacy model). Registered handle + secret required.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | max results (default 50, max 200) | |
| since | Yes | ISO 8601 timestamp | |
| handle | Yes | ||
| secret | No | ||
| namespace | No | optional filter to one namespace |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description's job is to add context. It adds that the tool returns creates/updates/deletes, is scoped to namespaces the handle has written to, and requires authentication. This provides behavioral context beyond the annotations, though it omits details on pagination or error behavior.
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 two sentences, front-loaded with the core purpose ('Incremental sync: returns memory entries...'), and every sentence earns its place with no redundancy. It is appropriately sized and structured.
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 5 parameters and no output schema, the description explains the core functionality, scope, and auth, but lacks details on pagination (limit parameter), expected output format, and behavior when no changes occur. It is adequate but could be more complete for a tool with moderate complexity.
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 60% (3 of 5 params have descriptions). The description adds that 'handle' and 'secret' are for authentication and that 'namespace' is an optional filter, but it does not elaborate on format or behavior beyond the schema. This provides marginal added value 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 clearly states the verb 'returns' and the resource 'memory entries that have been created, updated, or deleted since the given timestamp'. It specifies the scope ('scoped to namespaces your handle has explicitly written to') and distinguishes it from siblings like list_memory or recall_memories by emphasizing 'incremental sync' and the timestamp-based delta.
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 implies its use for incremental syncing by mentioning 'since the given timestamp' and the privacy model. However, it does not explicitly state when not to use this tool or name alternatives, leaving the agent to infer from the context. The mention of 'Registered handle + secret required' provides a usage prerequisite.
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.
Many tools serve similar purposes (e.g., web_read vs browse_read, web_discover vs browse_discover, research vs web_search + browse). Descriptions help differentiate, but the overlap is notable.
Most tools use a consistent verb_noun snake_case pattern (e.g., archive_message, browse_navigate). Minor deviations like standalone 'browse' and 'identity' are acceptable.
57 tools is very high for a single server, even with discover_tools. The broad domain coverage does not justify the count; it feels overloaded.
Covers identity, memory, browsing, human tasks, errands, messaging, and research comprehensively. Minor gaps might exist (e.g., no explicit agent-to-agent contract tools), but core workflows are well-supported.