get_checkpointsRetrieve decision checkpoints for a session. Returns the linked list of checkpoints in reverse chronological order. Use this to resume work from a prior checkpoint after session failure or handoff.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| session_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It states the return format ('linked list') and ordering ('reverse chronological'), which is valuable context. However, it does not explicitly confirm non-mutating behavior or describe error outcomes, so it falls short of a perfect score.
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 extremely concise: two sentences, front-loaded with the primary action, and every word earns its place. No fluff or repetition.
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?
Core purpose and use case are well covered, and the output schema exists so return values are documented elsewhere. However, the missing explanation of the 'limit' parameter and lack of any error or edge-case context make it only partially complete for a 2-parameter tool.
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 coverage is 0%, so the description must compensate. It implies the meaning of session_id via 'for a session,' but completely ignores the 'limit' parameter, leaving its purpose and interaction unclear. This is a significant 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 'Retrieve' with a clear resource 'decision checkpoints for a session,' and adds distinguishing details like 'linked list' and 'reverse chronological order.' It clearly differentiates from siblings such as get_decision_context or get_audit_trail.
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?
Provides an explicit use case: 'Use this to resume work from a prior checkpoint after session failure or handoff.' This gives strong situational guidance, but does not explicitly mention when not to use it or name alternative tools.
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.
Several tools have overlapping purposes: check_claim and memory_claim_check are the same function with different tiers, get_freshness_report and memory_freshness_report are duplicates, get_correction_chain and compare_versions both trace history, and investigate_question subsumes many other retrieval tools. This will cause agent misselection.
Most tools follow a verb_noun pattern (get_constraints, declare_constraint, sync_pull, etc.). Exceptions like memory_claim_check, memory_freshness_report, session_debrief, and verify_before_acting deviate but are relatively few. Overall the naming is readable and mostly predictable.
75 tools is excessive for a memory server. Many are highly niche or direct duplicates (e.g., paid/free versions of the same function). The count far exceeds typical well-scoped servers and introduces cognitive overhead without proportional value.
The server covers a wide array of memory, constraint, decision, skill, and sync operations, which is impressive. However, there are notable gaps: no direct delete or edit for memory facts (only corrections/versioning), and no bulk enumeration of all stored items. The redundancy in retrieval tools also suggests an incomplete design.