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 already provide destructiveHint=true and idempotentHint=true, covering safety profile. The description adds context by specifying what gets destroyed—'a previously stored memory'—and frames the action as clearing sensitive data. This goes beyond the structured fields without contradicting them.
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. The first states the exact action and resource; the second gives usage context and sibling pairing. No wasted words, front-loaded with the core purpose.
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?
This is a simple 1-parameter tool with no output schema. Annotations thoroughly cover destructive and idempotent behavior. The description explains the memory metaphor, when to use it, and how it relates to remember/recall, making it fully self-contained for an agent.
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 description coverage is 100%: the 'key' parameter is already described as 'Memory key to delete.' The description's 'by key' reinforces this but adds no new semantic detail (e.g., format, examples, or behavior when key is missing). Baseline 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 opens with 'Delete a previously stored memory by key,' which is a specific verb and resource. It clearly distinguishes this from sibling tools 'remember' (store) and 'recall' (retrieve) by identifying the destructive action (delete).
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 provides explicit use cases: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also names collaborating tools: 'Pair with remember and recall,' giving clear guidance on when to use this tool versus 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 overlapping purposes (e.g., ai_visibility_check and scan_competitor_ai_presence; ask_pipeworx, ask_pipeworx_grounded, and deep_research). However, detailed descriptions and specific use cases help agents distinguish between them in most cases.
All tools use snake_case naming consistently, e.g., ask_pipeworx, compare_entities, govcon_agency_landscape. The pattern is uniform across the entire set.
With 33 tools, the set is slightly over the typical well-scoped range. While many tools serve distinct purposes, some seem redundant (e.g., memory tools, multiple research tools), making the count feel a bit heavy.
The tool surface covers a broad range of research and intelligence domains but lacks actionable tools for core government contracting tasks like submitting bids or tracking contract performance. Several obvious operations (e.g., user profile management, submission tools) are missing.