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 the destructive nature ('Delete') and adds context about clearing 'sensitive data,' which enriches the behavioral profile beyond the annotations (destructiveHint=true, idempotentHint=true). It does not mention side effects like irreversibility, but the annotations already cover the core safety aspects.
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 first states the action, the second provides usage conditions, and the third names related tools. Every sentence adds value, no filler or repetition.
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 single-parameter delete operation with strong annotations and an explicit description, this is largely complete. It covers the action, the trigger, and related tools. The lack of an output schema is compensated by the straightforward nature of the operation, though it never states what happens after deletion (e.g., success confirmation).
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%, with 'Memory key to delete' fully explaining the purpose of 'key.' The description reinforces this with 'by key' and 'previously stored memory' without adding significant new meaning. Baseline 3 is appropriate given the high schema coverage.
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+resource combination that clearly distinguishes this from sibling tools like 'remember' and 'recall.' It also implies the scope of operation (existing memory) and the parameter (key).
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: 'when context is stale, the task is done, or you want to clear sensitive data.' Also provides guidance on complementary tools: 'Pair with remember and recall.' This meets the 'when/when-not/alternatives' criterion, even though it doesn't mention a when-not.
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 ORCID-specific tools (record, search, works, work) are reasonably distinct, but the set is dominated by unrelated Pipeworx/Polymarket tools, several of which overlap heavily (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, suggest_questions). ask_pipeworx_beta is explicitly described as currently identical to ask_pipeworx, creating genuine misselection risk.
Naming conventions are mixed with no consistent pattern: nouns like 'record', 'work', 'works', and 'education' sit alongside snake_case verb phrases like 'search_within', 'validate_claim', and 'generate_llms_txt', plus proprietary 'ask_pipeworx' / 'pipeworx_feedback' names. While readable, the styles are inconsistent enough that an agent cannot predict tool names from the domain.
37 tools is far too many for a server scoped as 'Orcid': only roughly 7 tools (record, works, work, education, employment, search, search_within) actually relate to ORCID. The remaining ~30 tools cover prediction markets, npm dependencies, AI visibility, and generic Pipeworx/Polymarket functionality, which is a severe scope mismatch.
For read-only ORCID access, the surface covers full records, works, education, employment, and registry search, with semantic search over fetched records as a useful addition. However, it lacks other common ORCID activity types (funding, peer review, distinctions), profile metadata beyond summaries, and any create/update/delete lifecycle operations, leaving notable gaps for a server claiming to serve ORCID data.