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 and idempotentHint=true. The description adds context about usage scenarios but no additional behavioral details (e.g., error handling, outcomes).
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?
Extremely concise: one sentence for purpose, a list of usage contexts, and pairing info. No 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 simple tool with one parameter and no output schema, the description covers purpose, usage, and relationships. No gaps.
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% and the schema description for 'key' is sufficient. The tool description adds no extra meaning beyond 'by key'.
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 verb 'delete', the resource 'memory', and the method 'by key'. It distinguishes from sibling tools like 'remember' and 'recall'.
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'. Also mentions pairing with 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 tools have nearly identical purposes: ask_pipeworx and ask_pipeworx_beta are explicitly identical, polymarket_arbitrage and polymarket_edges both scan for betting opportunities, and ai_visibility_check overlaps with scan_competitor_ai_presence. The long descriptions help, but an agent must read carefully to distinguish the meta-routers (ask_pipeworx, deep_research, discover_tools, suggest_questions) from each other.
The overwhelming majority use lowercase snake_case with a verb-first or domain-prefixed noun pattern (ask_pipeworx, sec_regulations_search, polymarket_edges). Minor deviations like entity_profile, recent_alerts, and ai_visibility_check are noun-first, and sec_regulation vs sec_regulations_search is slightly inconsistent, but the overall style is predictable.
At 33 tools this exceeds the 25-tool threshold for 'too many', and most are unrelated to the server's stated name 'Sec Regulations'—only sec_regulation and sec_regulations_search fit that label. While each tool has a defined purpose, the set feels like several distinct servers (research, betting, memory, subscriptions) crammed into one.
For a general data-research platform, the surface is broad: Q&A routers, entity resolution/profiles, comparisons, validation, memory, subscriptions, and domain-specific tools. But the SEC-regulation focus implied by the server name is severely under-served, and there's no direct tool to fetch a raw document by citation/URI outside of the ask_pipeworx router. The Polymarket cluster is over-built relative to other data domains.