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?
The annotations already declare destructiveHint=true and idempotentHint=true, which the description complements by explaining that the tool deletes stored memories. It adds context about clearing stale/done/confidential data, which is beyond the annotations. No contradiction is present.
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 concise at two sentences, front-loading the action and then adding usage guidance. No extraneous text, though the pairing advice could be integrated into the guidelines section. Efficient overall.
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 1-parameter tool with full schema coverage and annotations that cover safety, the description provides sufficient context. It lacks mention of return behavior, but this is not critical for a delete operation. The description is adequate.
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 has 100% coverage, fully documenting the 'key' parameter as a string. The description adds no additional meaning beyond 'memory key to delete,' so it does not contribute beyond the schema. 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 clearly states that the tool deletes a previously stored memory by key ('Delete a previously stored memory by key'), using a specific verb and resource. It distinguishes itself from sibling tools by explicitly mentioning 'Pair with remember and recall,' which are listed among the siblings.
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 usage scenarios: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It does not specify when not to use or suggest alternatives, but the given context is clear and useful for a simple deletion tool.
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.
Most tools have clearly distinct purposes (entity_profile, compare_entities, ask_pipeworx, etc.). However, ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are very similar, and suggest_questions/discover_tools overlap slightly. Overall, tools are well-disambiguated with only minor ambiguity.
All tool names use snake_case, but the pattern is inconsistent: some start with a verb (ask_, validate_), others with a noun (entity_, bet_). Several are noun_noun (entity_profile), and some are single verbs (remember). No consistent verb_noun pattern across the set.
33 tools is excessive for a server named 'Isbn' that only has 2 ISBN-specific tools. The majority are from Pipeworx, creating scope mismatch. Multiple redundant tools (three ask_pipeworx variants, several polymarket tools) inflate the count unnecessarily.
For a server named 'Isbn', completeness is very low—only conversion and validation are provided; no metadata lookup or other ISBN-related features exist. The Pipeworx tools themselves are comprehensive, but they do not align with the server's implied domain.