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?
The description adds context beyond annotations by noting the use case for clearing sensitive data. Annotations already indicate destructiveHint=true and idempotentHint=true, and the description aligns with these without contradiction.
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 core action, and contains 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 guidelines, and context completely. Annotations further fill in behavioral details.
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 description adds no additional meaning to the parameter beyond what the input schema provides. Schema coverage is 100%, so baseline is 3.
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 'Delete a previously stored memory by key', specifying the verb (delete), resource (memory), and method (by key). It also mentions pairing with 'remember' and 'recall', distinguishing it from sibling tools.
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 does not explicitly mention when not to use, but provides sufficient context.
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 are near-duplicates by name and function, notably ask_pipeworx vs ask_pipeworx_beta, and the dense Polymarket family (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread). Long descriptions help, but an agent cannot reliably pick between these without reading closely.
Almost all names are lowercase_snake_case and mostly verb-leading (discover_tools, resolve_entity, unsubscribe), but there are noun-first exceptions (entity_profile, recent_changes, pipework_trending) and several phrasal or compound forms. This is a minor deviation from a clean verb_noun pattern rather than a chaotic mix.
31 tools is over the heavy threshold, and the set feels bloated: multiple query routers, a half-dozen overlapping Polymarket tools, and two AI-visibility probes that could be merged. The count is especially hard to justify for a server named Tools 'OutLook Contacts', since none are contact management.
For the server's stated domain, Outlook Contacts, there are zero tools in that domain — no create contact, no list contacts, no update, no delete, no folders or mailboxes. Even though the actual Pipework toolkit is broad for its own domain, this set fails its declared intend domain entirely.