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?
The description discloses that it deletes a stored memory and adds context about clearing sensitive data, which goes beyond the annotations' destructiveHint and idempotentHint. It does not contradict annotations; rather, it reinforces them. The added usage context (stale context, task completion) provides behavioral nuance beyond the raw structured metadata.
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?
Three short sentences: the action, when to use, and related tools. Every sentence adds value, with no filler or repetition. It is front-loaded with the core action and efficiently conveys all necessary information.
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 deletion tool with no output schema, the description covers purpose, usage, and pairing, while annotations cover destructive/idempotent behavior. The description is complete and leaves no critical gaps for an agent to invoke the tool correctly.
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 input schema already provides 100% coverage with the key description 'Memory key to delete,' making the parameter semantics clear. The description's 'by key' adds little beyond the schema. Baseline 3 is appropriate because the schema does the heavy lifting.
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 begins with 'Delete a previously stored memory by key,' which clearly states the verb (delete) and resource (previously stored memory) with the mechanism (by key). It distinguishes itself from sibling tools remember (store) and recall (retrieve), making the purpose unambiguous.
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: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also names alternatives/companions with 'Pair with remember and recall,' giving the agent clear decision guidance.
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.
Multiple tool clusters are nearly indistinguishable: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded overlap heavily (beta is explicitly identical right now), and five polymarket tools (arbitrage, edges, edge_tracker, fill_risk, kalshi_spread) all concern prediction-market edge detection with fuzzy boundaries. entity_profile, recent_changes, and compare_entities also blur together for company research. Only the book tools are cleanly distinct, but they are drowned by the surrounding ambiguity.
Most tools follow a consistent snake_case pattern and generally lead with a verb or clear noun (search_books, get_book, subscribe, unsubscribe, validate_claim, resolve_entity). A few depart from the verb-first convention (entity_profile, bet_research, pipeworx_trending, polymarket_edges) but the deviations are minor and do not hinder readability.
35 tools is already heavy, but the critical problem is scope: the server is named gutendex (a book API) yet only 4 of 35 tools relate to books, with the other 31 forming an unrelated Pipeworx data/research/prediction-market suite. The count is inappropriate for the advertised purpose — it feels like two or three separate servers crammed into one.
For the gutendex domain, the book tools are thin: search, get, popular, and topic browsing exist, but common Gutendex capabilities like author browsing, language filtering, sorting, and pagination controls are missing. For the actual Pipeworx suite the surface is broad, but the server's stated purpose is gutendex, and the overwhelming majority of tools are completely off-topic, creating a severe coverage mismatch.