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 provide destructiveHint=true, so description's 'Delete' adds no new behavioral info. It adds context about use cases, but not unique behavioral traits beyond 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 sentences: first states purpose, second provides usage guidance. No wasted words, front-loaded with key 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?
Simple single-param tool with annotations covering destructiveness. Missing mention of idempotency (idempotentHint=true) or behavior on missing key, but completeness is high given tool simplicity.
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 description 'Memory key to delete'. Description only says 'by key', adding no extra meaning beyond schema. Baseline 3 applies.
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?
Description clearly states 'Delete a previously stored memory by key', specifying verb and resource. It distinguishes from siblings like remember and recall by pairing them, indicating this is the deletion counterpart.
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?
Explicitly states when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Pairs with remember and recall, guiding agent on alternatives.
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 tool clusters are hard to distinguish: ask_pipeworx_beta explicitly states it 'currently matches ask_pipeworx exactly', creating a literal duplicate, and the six polymarket_* tools all orbit 'find a trading edge on prediction markets' with only subtle differences in scope. ask_pipeworx / ask_pipeworx_grounded / validate_claim / deep_research also overlap on fact-finding, and discover_tools vs suggest_questions both serve 'what can I do here' discovery. The memory trio and subscription lifecycle are clean, but the central Q&A and prediction-market areas carry real misselection risk.
The set mixes several incompatible conventions: bare verbs (query, recall, forget, remember), noun phrases (entity_profile, dataset_info), verb_noun pairs (search_datasets, compare_entities, validate_claim), and prefixed families (polymarket_*, ask_pipeworx_*, pipeworx_*). Family prefixes provide local consistency, but there is no unifying pattern across the server, and the three SNCF tools follow a different style from the Pipeworx tools. The naming reads as several mini-servers bolted together rather than one coherent API.
At 34 tools, the count exceeds the comfortable range and is inflated by genuine redundancy: ask_pipeworx_beta duplicates ask_pipeworx, ask_pipeworx_grounded is a paid variant, scan_competitor_ai_presence wraps ai_visibility_check, and six Polymarket tools could plausibly be consolidated. The server name promises a narrow SNCF data scope, yet 31 of 34 tools serve an unrelated universal data / prediction-market platform, making the count feel both bloated and mismatched to the server's stated identity.
For the dominant inferred domain (Pipeworx structured-data Q&A, research, and prediction markets), the surface is quite complete: discovery, routing, grounded answers, deep research, claim verification, entity resolution, profiles, comparisons, change feeds, subscriptions, and memory are all present. However, relative to the server's stated name 'Data Sncf', the SNCF surface is minimal (search -> metadata -> query) with no update feeds, record-level fetch, or live railway status, and the two domains never connect. The orphaned single-purpose tools (generate_llms_txt, scan_dependency) further fragment the sense of a coherent domain.