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 include destructiveHint=true and readOnlyHint=false, so the destructive nature is known. The description adds useful context beyond that: it clarifies the target as 'previously stored memory' and the rationale for clearing 'sensitive data the agent saved earlier.' This provides extra behavioral context without contradicting the annotations.
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 long and front-loaded with the action verb ('Delete'). Every sentence contributes: the first defines the operation, and the second provides usage context and sibling relationships. There is no redundancy or filler.
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 and no output schema, the description adequately covers the purpose, usage timing, and relationship to sibling tools. It does not mention return behavior or edge cases (e.g., nonexistent key), but the tool's simplicity makes this acceptable. A higher score would require explicit handling of such 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?
Schema coverage is 100% for the single 'key' parameter, which is described as 'Memory key to delete.' The description's mention of 'by key' and 'previously stored memory' adds only slight semantic enrichment. Since the schema already fully documents the parameter, a baseline score 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 opens with the specific verb+resource: 'Delete a previously stored memory by key.' It clearly distinguishes the tool from siblings like 'remember' and 'recall' by specifying the delete operation and key-based targeting. This leaves no ambiguity about what the tool does.
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 concrete when-to-use scenarios: 'when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also positions the tool relative to siblings with 'Pair with remember and recall.' However, it does not explicitly state when *not* to use the tool, so it falls short of the full 5.
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.
Many tools have overlapping purposes (e.g., ask_pipeworx, ask_pipeworx_grounded, deep_research; multiple Polymarket tools). The memory tools (remember/recall/forget) are generic and could be confused with each other. Overall, there is significant ambiguity in tool selection.
Most tool names use snake_case, but there is no strong verb_noun pattern. Some are simple nouns (languages, search) while others are verbs (forget, recall). The naming is readable but not highly consistent.
With 34 tools, the set is far too large for a Tatoeba server. Only 4 tools (search, sentence, translations, languages) are actually related to Tatoeba; the rest cover unrelated domains (Pipeworx data, Polymarket, AI visibility). This is an extreme mismatch.
For the Tatoeba domain, the 4 tools cover basic functionality but lack operations like adding or editing sentences. The overwhelming presence of irrelevant tools makes the surface feel incomplete and disjointed for the server's stated purpose.