Store a distilled knowledge artifact (lesson, pattern, anti_pattern, heuristic, or reasoning_trace).
| Name | Required | Description | Default |
|---|---|---|---|
| why | No | ||
| kind | Yes | ||
| tags | No | ||
| outcome | No | ||
| problem | Yes | ||
| solution | No | ||
| workspace | No | Project/workspace to scope to (defaults to this connection's workspace; isolates work streams within your account) | |
| confidence | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. The verb 'Store' conveys a write/persist operation, but nothing is said about whether storing an artifact with the same problem/kind overwrites existing data, whether deduplication occurs, whether workspace scoping isolates artifacts, or what the operation returns. For a memory tool these are significant unspecified behaviors.
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?
A single 12-word sentence that front-loads the core concept ('Store a distilled knowledge artifact') before enumerating the kinds. The parenthetical is partly redundant with the schema enum, but it serves fast scanning when the schema isn't visible, so it earns its place. No wasted words otherwise.
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?
For an 8-parameter tool with no annotations and no output schema, the description is too thin. It answers 'what does it do' but not 'when should I use it', 'what do the required fields mean', or 'what are the side effects'. The large sibling list and the required 'kind'+'problem' combination demand more guidance than a single clause provides.
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 13% (only 'workspace' is documented), so the description must compensate — and it barely does. The parenthetical repeats the 'kind' enum values already in the schema, adding no meaning. The phrase 'distilled knowledge artifact' mildly contextualizes problem/solution/why, but the description never explains semantics for the required 'problem' field, nor for 'confidence', 'outcome', 'why', or 'solution'.
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 a specific verb ('Store') and resource ('distilled knowledge artifact') and enumerates the artifact kinds. It is clear and internally coherent, but it does not explicitly differentiate from semantically overlapping siblings like wyrm_capture, wyrm_vault_put, or wyrm_truth_set — the 'distilled' qualifier implies a distinction but never names it.
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?
No guidance is given about when to use this tool versus its siblings. Given a sibling list of 29 tools with several overlapping storage semantics (wyrm_capture, wyrm_vault_put, wyrm_truth_set, wyrm_decision_trace), an agent has no way to tell which tool fits a given situation. The description does not state prerequisites, exclusions, or alternative routing.
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.
Multiple tools have heavily overlapping purposes: wyrm_all_quests vs wyrm_quest_list, wyrm_decision_downstream vs wyrm_decision_trace, and wyrm_recall vs wyrm_search are near-duplicates in behavior. wyrm_capture also overlaps with wyrm_remember, wyrm_truth_set, wyrm_quest_add, and wyrm_decided_because, making it hard for an agent to reliably pick the right tool.
Most names share the wyrm_ prefix and many follow a resource-action pattern like truth_set, quest_list, and failure_record. However, the pattern is broken by names like wyrm_all_quests, wyrm_decided_because, wyrm_context_build, wyrm_remember, and wyrm_capture, mixing noun-first, verb-first, and non-patterned names.
At 31 tools this is above the heavy threshold, and several tools appear redundant or mergeable, such as wyrm_all_quests/quest_list, decision_trace/downstream, capture/remember, and context_build/session_prime. The breadth is real, but the count feels inflated by overlapping entry points rather than distinct capabilities.
The tool surface covers core lifecycles well: quests have add/claim/update/complete/release, failures have record/check/list/resolve, decisions have record/trace/invalidate, and the vault has full get/put/list/delete. The main gaps are the lack of delete/update for memory artifacts and ground truths, and no explicit way to remove stale artifacts.
