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 the types of memories to delete (stale, task-complete, sensitive) and implies it only affects previously stored data. No contradiction with annotations, and the additional nuance about sensitive data is valuable.
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 plus a short pairing note. It is front-loaded with the action and usage, with no filler or redundant information. Every sentence adds value.
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 tool with annotations covering destructiveness and idempotency, the description is complete. It covers usage cases, pairing, and the nature of the operation. The lack of an output schema is acceptable for a delete operation, and the description does not need to explain return values. Minor gap: it doesn't explicitly state behavior for missing keys, but idempotentHint implies safe repetition.
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 schema fully covers the single parameter 'key' with description 'Memory key to delete' and an example. The description mentions 'by key' but does not add deeper semantics about key format, naming conventions, or deletion behavior on missing keys. Baseline 3 is appropriate since schema coverage is 100%.
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 clearly states 'Delete a previously stored memory by key' with a specific verb and resource, and distinguishes from sibling tools like remember and recall by focusing on deletion. The action is unambiguous and not a tautology.
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?
Provides explicit when-to-use guidance: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' Also mentions pairing with remember and recall, which helps the agent understand the tool's role in the memory workflow.
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 fuzzy boundaries: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all overlap on 'find and query data,' while the five polymarket_* tools plus bet_research form a heavily overlapping prediction-market cluster. The three genuine InterPro tools are clear, but an agent would frequently struggle to pick the right meta-tool.
Most tools follow a readable snake_case verb-first pattern like compare_entities, resolve_entity, and validate_claim. However, bare verbs (remember, forget, recall), product-prefixed nouns (pipeworx_feedback, pipeworx_trending), and variant suffixes (ask_pipeworx_beta, ask_pipeworx_grounded) break the pattern enough to feel inconsistent.
34 tools is well above the typical well-scoped range, and many tools duplicate or partially overlap each other's functionality. The count is further inflated by unrelated domains—AI visibility, prediction markets, memory, subscriptions, package auditing—bundled into a server nominally named 'Interpro.'
The InterPro subset (search_entries, get_entry, entries_for_protein) is minimal and lacks obvious protein/proteome-level operations, while the rest of the server covers so many unrelated domains that no single domain has clear end-to-end coverage. The Pipeworx query side is broad, but the overall surface feels like several incomplete toolsets merged rather than one complete product.