update_constraintUpdate an existing constraint. Content changes create a new version (append-only). Status-only changes update in place. This is a mutation operation.
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | ||
| status | No | ||
| evidence | No | ||
| severity | No | ||
| assertion | No | ||
| expires_at | No | ||
| constraint_id | Yes | ||
| assertion_structured | No | ||
| review_interval_days | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavior itself. It does so by stating that content changes create a new append-only version while status-only changes update in place, and it explicitly calls out that this is a mutation operation. This is non-obvious behavioral context that goes beyond the tool name, though it could be more specific about what counts as 'content.'
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 three short sentences. The first sentence delivers the core purpose, and the following two sentences add valuable behavioral nuance. No wasted words 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?
Despite having an output schema, the tool has 9 parameters, including nested objects and enums, with no annotations. The description only covers the high-level versioning behavior and omits how to reference the constraint (constraint_id), which parameters are content vs status, and the effect of each field. This is insufficient for correct invocation of a complex update 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 description coverage is 0%, so the description must compensate by explaining parameter roles. It only vaguely distinguishes 'content changes' from 'status-only changes' without mapping them to any of the 9 parameters (e.g., assertion, evidence, severity, status). Agents have no guidance on which fields trigger versioning or how to construct updates, leaving a critical 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 opens with 'Update an existing constraint,' a specific verb+resource pair that clearly indicates the tool's purpose. It also notes 'Content changes create a new version (append-only)' and 'Status-only changes update in place,' which distinguishes this tool from sibling tools like declare_constraint or get_constraints.
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 phrase 'existing constraint' implies use for modifying an already-declared constraint, which provides clear context separating it from declare_constraint. However, it does not explicitly name alternatives or provide exclusion criteria, so it falls short of a full 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.