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 declare destructiveHint=true and idempotentHint=true; description confirms deletion and adds context about sensitive data and usage scenarios, complementing annotations well.
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 with no redundant information, front-loaded with purpose and concise usage guidance.
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 delete operation with one parameter and no output schema, the description fully covers purpose, usage, and pairing advice.
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 clear parameter description ('Memory key to delete'). Description does not add additional semantics beyond schema, 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?
Description uses specific verb 'Delete' and resource 'memory by key', clearly distinguishing from siblings 'remember' (store) and 'recall' (retrieve).
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 the tool (stale context, task done, clear sensitive data) and references siblings for 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.
The ask_pipeworx family (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research) has blurry boundaries — ask_pipeworx_beta is explicitly identical to ask_pipeworx today — and the six Polymarket tools (polymarket_arbitrage, polymarket_edges, polymarket_fill_risk, etc.) all operate in the opportunity-detection space. Extremely detailed descriptions help, but an agent could easily select the wrong variant.
Snake_case is used throughout and the polymarket_* and pipeworx_* clusters are internally consistent, but the set mixes verb-first names (ask_pipeworx, resolve_entity, validate_claim) with noun-first names (entity_profile, recent_changes, news, places) roughly evenly. The 'beta' suffix on a stable production tool and the adjective-noun 'deep_research' add further inconsistency.
At 34 tools this exceeds the 25+ threshold, and the count is padded with redundancy: three near-identical ask_pipeworx variants, ai_visibility_check wrapped by scan_competitor_ai_presence, and six overlapping Polymarket tools. The unusually broad multi-domain scope justifies more tools than a typical server, but several clusters could be consolidated.
The surface is thorough for a read-only data-access gateway: universal routing, grounded verification, entity resolution/profiles/comparisons, web/news/maps search, prediction-market analysis, memory CRUD, and a full subscription lifecycle. Minor gaps exist (no direct fetch tool for pipeworx:// citation URIs, no image/video Serper endpoints) but agents can work around them.