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 declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true, so the description's 'Delete' is consistent. It adds the 'clear sensitive data' context and pairing note, but does not disclose additional behavioral details such as behavior for nonexistent keys or side effects. This provides some value beyond annotations, warranting a 3.
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 two sentences, front-loaded with the action, and every phrase contributes value—purpose, usage conditions, and tool relationships. No redundancy or unnecessary words.
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 single-parameter delete tool with strong annotations (destructive, idempotent) and no output schema, the description fully covers purpose, usage, and relationships. The context signals confirm low complexity, so no further information is needed.
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 input schema has 100% coverage with 'Memory key to delete' directly describing the key parameter. The description adds 'previously stored memory' context but no extra syntax or format details beyond the schema. Baseline 3 applies because the schema carries the semantic load.
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 the tool's action: 'Delete a previously stored memory by key.' It uses a specific verb and resource, and the mention of pairing with remember and recall distinguishes it from complementary tools by establishing its unique destructive role.
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 provides explicit use cases: 'when context is stale, the task is done, or you want to clear sensitive data.' It also mentions pairing with remember and recall, but does not explicitly state when not to use the tool or name alternative 'instead' tools, so it falls short of a perfect 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 unclear boundaries: ask_pipeworx, ask_pipeworx_beta (currently functionally identical), ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all route to the same underlying catalog with only subtle differences. The Polymarket cluster (bet_research, polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread) also substantially overlaps in purpose, and the two unrelated domains (GIS vs. data/betting) make it worse.
Names are readable and form some predictable clusters (polymarket_* prefix, ask_pipeworx_* suffixes, subscribe/unsubscribe/list_subscriptions), but conventions are mixed: bare verbs (remember, forget, recall), noun_noun (layer_info, entity_profile, pipeworx_feedback), verb_noun (query_layer, search_datasets), and adjective_noun (deep_research, recent_alerts). No single pattern dominates, though nothing is chaotic.
34 tools is well above the 25+ threshold for a heavy surface, and the count is not justified by the server's stated identity: only 3 of 34 tools (search_datasets, layer_info, query_layer) relate to ArcGIS Glasgow. The remaining 31 tools belong to several unrelated domains (Pipeworx data querying, Polymarket betting, AI visibility, memory, npm scanning), making the effective scope far too broad.
For the server's named ArcGIS Glasgow domain, the surface is thin: search, schema inspection, and query are present, but there is no way to list all datasets, no spatial querying, and no write/update capability. Meanwhile the 31 non-GIS tools create a sprawling second server's worth of functionality, so the set as a whole has no coherent domain whose coverage can be judged complete.