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?
Annotations already provide destructiveHint=true and idempotentHint=true. Description adds context about why to use the tool (e.g., clear sensitive data) without contradicting annotations. It does not elaborate on irreversibility, but the destructive hint covers that.
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 concise sentences: first states purpose, second provides usage guidelines and sibling context. No wasted words, front-loaded.
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?
Given the simple tool (one param, full schema coverage, annotations), the description covers what it does, when to use it, and related tools. It doesn't describe return value, but for a delete operation that is acceptable.
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?
Input schema has 100% coverage with a clear description 'Memory key to delete'. The tool description does not add additional semantic information beyond the schema, so 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?
Description clearly states 'Delete a previously stored memory by key', which is a specific verb+resource. It distinguishes from siblings like remember and recall by specifying the action of deletion.
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?
Explicit usage conditions provided: 'Use when context is stale, the task is done, or you want to clear sensitive data'. Also pairs with remember and recall, giving clear context.
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 occupy heavily overlapping territory: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, bet_research, validate_claim, and even entity_profile/compare_entities all route questions to similar underlying data and could easily be misselected. The Polymarket suite adds another cluster of near-synonymous tools. Descriptions are detailed, but the boundaries require careful reading to keep straight.
Tool names mix imperative verbs (remember, subscribe, resolve_entity, validate_claim), noun-phrase descriptors (entity_profile, recent_changes, polymarket_edges), and time-utility names (now, from_timestamp, to_timestamp, relative_time). All-lowercase snake_case is consistent, but there is no unified verb_noun or domain-prefix pattern across the set.
35 tools is heavy and exceeds the comfortable 3-15 range, and most of them are unrelated to the server name 'Timestamp,' which adds confusion. The broad Pipeworx data scope justifies more than a tiny utility server, but the count still feels overstuffed and will burden tool selection.
For the broad data-research and prediction-market domain the set actually covers, the lifecycle is fairly complete: query, deep research, entity profiles, comparisons, claim validation, subscription management, and memory storage all have working operations. However, the surface is sprawling and includes one-off tools like generate_llms_txt and scan_dependency that do not fit any coherent domain, making completeness hard to assess and leaving a fuzzy, fragmented impression.