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.
Input schema / examplesAdded value: +[
+ {
+ "key": "user_research_topic"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide destructiveHint=true and idempotentHint=true, so the description's 'Delete' adds little beyond that. It does not elaborate on permanence or side effects, leaving the annotations to carry the behavioral weight.
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, no fluff, front-loaded with the action and purpose. Every sentence contributes meaning.
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 tool with one parameter, high schema coverage, and clear annotations, the description is sufficiently complete. It states purpose, usage context, and sibling relationships. No output schema, so return value explanation is not 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?
Schema coverage is 100% with a description for the 'key' parameter. The description adds only 'by key', which is redundant. It does not clarify format or constraints beyond what the schema provides. Baseline score of 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 states 'Delete a previously stored memory by key', which clearly identifies the verb and resource. It mentions pairing with 'remember' and 'recall' but does not explicitly distinguish when to use this over those siblings. The purpose is clear but lacks direct sibling differentiation.
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 describes when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also suggests pairing with related tools, providing implicit context for alternatives. No explicit 'when not to use' statement, but the given guidance is specific and actionable.
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 have unclear boundaries: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route to the same 5,724 tools with only subtle behavioral differences, and bet_research, polymarket_edges, polymarket_arbitrage, and polymarket_kalshi_spread heavily overlap around prediction-market opportunity discovery. entity_profile, compare_entities, and recent_changes also fan out across the same SEC/news/patent sources, making selection ambiguous for agents.
Naming mixes multiple conventions: snake_case verb_noun for odds tools (get_events, list_sports), vendor-prefixed clusters (ask_pipeworx_*, pipeworx_*, polymarket_*), and a few reversed noun-verb names like bet_research. CamelCase is used in ai_visibility_check and generate_llms_txt adds another style. Only the polymarket_* and pipeworx_* families are internally consistent, but the overall pattern is chaotic.
37 tools is well beyond the typical well-scoped server, and the count feels inflated by unrelated meta-tools (suggest_questions, discover_tools, pipeworx_feedback, pipeworx_trending, generate_llms_txt, scan_dependency, remember/recall/forget) that have nothing to do with the server's stated 'Odds Api' purpose. The actual odds surface is only ~5 tools, so the vast majority of the catalog is off-scope padding.
The core odds domain is well covered: list_sports, get_events, get_odds, get_event_odds, and get_scores form a coherent lifecycle, plus quota introspection. However, for the server's actual broad-research scope there are noticeable gaps (e.g., no direct single-filing fetch tool despite heavy SEC coverage, a lone npm-dependency tool with no surrounding ecosystem, and no historical/past-odds endpoint), and the heterogeneous domains make completeness uneven.