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 declare destructiveHint=true and idempotentHint=true, so the description doesn't need to restate these. It adds the motivation of 'clear sensitive data' but does not disclose additional behavioral traits such as error handling when the key doesn't exist or whether deletion is permanent. Given the annotations cover the safety profile, this is adequate but not rich.
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, starting with the action verb, and contains no redundant words. Every sentence adds value: the first states what it does, the second gives usage guidance and sibling context.
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 no output schema, the description covers the essential aspects: what it does, when to use it, and complementary tools. Annotations provide the destructive/idempotent profile, so no further behavioral description is needed.
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 a single 'key' parameter described as 'Memory key to delete.' The tool description's 'by key' aligns with this. No additional semantics are needed beyond the schema, so the baseline of 3 applies.
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 clearly states a specific verb (delete), resource (memory), and scope (by key). It explicitly distinguishes this from the sibling tools 'remember' and 'recall' by indicating it is the removal counterpart.
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 gives concrete when-to-use conditions: 'when context is stale, the task is done, or you want to clear sensitive data.' It also suggests pairing with 'remember and recall,' showing awareness of the tool ecosystem and guiding appropriate use.
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.
Multiple tools serve near-identical purposes: ask_pipeworx and ask_pipeworx_beta are explicitly identical today, ask_pipeworx_grounded and deep_research overlap heavily, and bet_research/polymarket_edges/polymarket_arbitrage all scan prediction-market opportunities. An agent reading these names and descriptions cannot reliably pick one tool without reading very long descriptions.
The names are all lower_snake_case, but the naming style is not consistent across the server: verb_noun (get_holidays, validate_claim), bare noun phrases (next_holidays, entity_profile, bet_research), is/are predicates (is_today_holiday), and separate pipeworx/polymarket prefixed groups. There are recognizable subgroups, but no coherent naming convention unifies the full tool surface.
34 tools is over the healthy range and the majority have nothing to do with holidays; they belong to a broader Pipeworx data, prediction-market, and subscription platform. The holiday-specific surface is only three tools buried inside a much larger, unrelated toolkit, making the server feel overloaded and mislabelled.
For the actual holiday domain the core read workflows are covered: all public holidays by country/year, today's holiday status, and upcoming holidays. A small gap is the lack of a supported-country/region listing or date-range filtering, but these are easily worked around because get_holidays returns the full year set.