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 provide destructiveHint=true and idempotentHint=true. The description adds context about why to delete (stale context, done tasks, sensitive data), which is beyond the annotations. No contradiction noted.
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 with no waste. The first sentence states the core action, and the second provides usage context and sibling relationships. Front-loaded and efficient.
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 clear annotations, the description is complete enough. It covers purpose, usage, and relationships to remember/recall. No output schema exists, so no need to explain return values.
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 does not add extra meaning beyond the schema's 'Memory key to delete', so baseline 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 clearly states the tool deletes a memory by key, using the verb 'Delete' and the resource 'memory'. It distinguishes from siblings by mentioning 'Pair with remember and recall', clarifying its role in the memory triad.
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 usage scenarios: when context is stale, task is done, or to clear sensitive data. Does not explicitly state when not to use, but the positive guidance is clear and sufficient for most cases.
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.
The Airtable tools are distinct, but the set is dominated by a large Pipeworx research family with multiple near-identical entries (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded) and several overlapping prediction-market tools (bet_research, polymarket_edges, polymarket_arbitrage). An agent would frequently struggle to pick the right tool among the many data-lookup and research options, especially given the server is supposedly named Airtable.
Naming conventions are mixed: some tools use verb_noun snake_case (airtable_create_record, list_subscriptions, resolve_entity), while others use domain-prefixed names (pipeworx_feedback, polymarket_edges) or bare verbs (remember, forget, recall, subscribe). There is no single predictable pattern across the set.
36 tools is heavy for any single server's scope, and the mismatch is worse because the server is named Airtable yet only 5 of 36 tools relate to Airtable. The rest form an unrelated Pipeworx/Polymarket/memory grab-bag, suggesting poor scoping and no clear purpose for the set as a whole.
For the stated Airtable domain, the surface is incomplete: records can be created, fetched, and listed, but there is no update_record or delete_record. For the broader Pipeworx/prediction-market domain the coverage is extensive but unfocused, and given the server's name the Airtable gap is glaring.