forgetDelete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Memory key to delete |
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?
Annotations already indicate destructiveHint=true and idempotentHint=true. The description adds behavioral context by clarifying the deletion is for clearing sensitive or stale data, which goes beyond the annotations.
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?
Two short sentences with no fluff. Every sentence adds value: first states the action, second provides usage context and sibling references.
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 a simple deletion tool with one parameter, no output schema, and adequate annotations, the description fully covers the necessary context—what, when, and how to use.
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 100% with a single parameter 'key' adequately described. The description does not add extra meaning to the parameter, so baseline 3 is appropriate.
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 'Delete a previously stored memory by key.' It uses a specific verb (delete) and resource (memory by key), and distinguishes from sibling tools 'remember' and 'recall' which are opposite actions.
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 explicitly tells when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data.' It also mentions alternatives by saying 'Pair with remember and recall.'
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.
Most tools have distinct purposes with detailed descriptions. However, the three ask_pipeworx variants (standard, beta, grounded) and the five polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread) have overlapping functionality that could confuse an agent if descriptions are not carefully parsed. The memory tools (remember, recall, forget) are clear. Overall, the set is mostly disambiguated.
Tool names use snake_case consistently, but naming patterns vary: some follow verb_noun (e.g., ai_visibility_check, compare_entities), others are noun_noun (e.g., bet_research, entity_profile), and a few are single verbs (e.g., recall, remember, forget, subscribe). This mixed pattern reduces predictability, though the names are still readable.
At 35 tools, the server is overly broad, covering Belgian rail, Pipeworx data queries, prediction markets, memory, subscriptions, and more. The server name 'Irail' suggests a focused rail toolset, but rail is only a small part. This scope mismatch and high tool count make it feel bloated and less coherent.
Within each subdomain, the tool surface is fairly complete. Belgian rail has journey planning, liveboard, train tracking, and disturbances. Data querying has universal, grounded, deep research, entity profiles, comparisons, recent changes, and claim validation. Prediction markets have arbitrage, edge detection, edge tracking, fill risk, and cross-venue spread. Memory and subscriptions are covered. Minor gaps exist (e.g., no tool for deleting entities or canceling orders), but overall coverage is strong.