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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, covering the operational safety profile. The description adds usage scenarios and 'previously stored' but does not disclose additional behavioral traits such as handling of non-existent keys, error behavior, or permanence. Given the annotations, the description's contribution is marginal, so a score of 3 is appropriate.
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 concise, with two sentences that are front-loaded with the core action ('Delete'). The first sentence defines the operation, the second provides usage guidance and sibling context. There is no redundancy or filler, and every sentence earns its place.
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 one-parameter deletion tool, the description provides essential context: purpose, when to use, and relationship to sibling tools. The annotations cover destructive and idempotent behavior, and the schema fully documents the parameter. It does not mention return values or error handling, but given the simplicity and annotation coverage, this is a minor gap.
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 fully documents the single required 'key' parameter with description 'Memory key to delete.' The description essentially restates this ('by key') and adds minimal semantic detail. With schema coverage at 100%, the baseline score of 3 applies; the description does not compensate or add beyond the schema.
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 a clear action ('Delete a previously stored memory by key'), specifying both the verb and resource. It distinguishes itself from sibling tools by mentioning 'Pair with remember and recall,' which places it within a memory-management family and makes its deletion role unambiguous.
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 states when to use the tool: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also references 'remember' and 'recall' as complementary tools, providing a clear mental model. However, it doesn't explicitly state when not to use it or contrast with alternatives beyond the pairing.
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 near-duplicate tool clusters exist: ask_pipeworx, ask_pipeworx_beta (explicitly identical right now), and ask_pipeworx_grounded overlap heavily, as do polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, and polymarket_kalshi_spread. The three ArcGIS tools (search_datasets, layer_info, query_layer) are distinct, but their purpose is drowned out by the unrelated Pipeworx data tools.
Most names use snake_case, but the pattern is inconsistent: some are verb_noun (ask_pipeworx, search_datasets, resolve_entity), some are noun_noun (layer_info, entity_profile, pipeworx_feedback), and some are adjective_noun (recent_alerts, recent_changes). Verbs are also inconsistent across similar actions (scan_ vs check_ vs compare_, and three different polymarket_ verbs plus a bare bet_research).
34 tools is already heavy, but the server is named Arcgis Pittsburgh and only 3 of the 34 tools relate to Pittsburgh GIS data; the other 31 belong to unrelated domains (Pipeworx data lookup, prediction markets, memory, npm auditing). This is an extreme scope mismatch — the tool count is far too high for the stated purpose and mostly irrelevant noise.
For the ArcGIS Pittsburgh domain, the surface has basic read coverage (search datasets, inspect layer schema, query records) but no update/delete/write operations and no geospatial analysis tools, which are significant gaps for a GIS server. The broader tool set is a grab bag of research, prediction-market, and memory features that don't form a coherent lifecycle for any single domain, so completeness cannot be assessed as a unified surface.