derive_from_factsSafe math and selection over a fact row set. Operations: sum, count, difference, max, min, latest, earliest. Pass the rows from enumerate_memory_facts and get a deterministic result with a computation trace. Removes arithmetic slop from totals, comparisons, and 'which is highest' questions.
| Name | Required | Description | Default |
|---|---|---|---|
| rows | Yes | ||
| operation | 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. It adds behavioral traits: 'Safe math' (non-destructive), 'deterministic result with a computation trace' (reliability and auditability). These go beyond what the schema provides, though it does not detail error cases or edge conditions.
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 concise sentences with front-loaded purpose, a list of operations, and a usage instruction. No redundant information.
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?
The description covers purpose, usage, and behavioral outcomes. With an output schema present, return values don't need explanation. It references the upstream tool enumerate_memory_facts, creating a complete workflow. Minor gaps: missing details on operation semantics for edge cases, but overall adequate for a simple aggregation 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?
The schema has 0% description coverage, so the description must compensate. It adds meaning to 'rows' by specifying they come from enumerate_memory_facts, and lists the operations that match the enum. However, it does not explain subtle semantics like what 'difference' computes or how 'latest' is determined, leaving some interpretation to the agent.
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 'Safe math and selection over a fact row set' and enumerates the operations (sum, count, difference, max, min, latest, earliest). It distinguishes itself from sibling tools by explicitly instructing to pass rows from enumerate_memory_facts, indicating a specific input source and use case.
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 provides clear context by saying 'Pass the rows from enumerate_memory_facts' and describes the type of questions it solves ('totals, comparisons, and which is highest'). However, it does not explicitly mention when not to use it or alternative tools, so it falls short of a 5.
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.