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 repeat them. It adds no behavioral context beyond the annotations—no mention of irreversibility, failure behavior, or key-not-found handling. It only adds usage guidance, which belongs to a different dimension. No contradiction with 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?
Two sentences, action is front-loaded, no filler. Every phrase earns its place: the delete operation, the 'by key' qualifier, and the usage trigger conditions plus sibling tools.
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?
The tool is simple (one required parameter, no output schema, no nested objects). The description covers what the tool does, when to use it, and how it relates to siblings. Annotations cover safety implications. Nothing essential is missing for this tool's complexity.
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%, and the single parameter 'key' is described as 'Memory key to delete.' The description reinforces 'by key' but adds no new semantic detail beyond the schema. Baseline 3 applies because the schema carries the full load.
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 begins with a specific verb and resource: 'Delete a previously stored memory by key.' This is unambiguous and distinguishes it from sibling tools like remember and recall, which store and retrieve memories respectively.
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 conditions are given: 'Use when context is stale, the task is done, or you want to clear sensitive data.' It also names complementary tools: 'Pair with remember and recall,' which signals when to use those alternatives and this tool's role in the workflow.
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.
Several tools have heavily overlapping purposes: ask_pipeworx and ask_pipeworx_beta are explicitly identical, ask_pipeworx_grounded and deep_research blur the query/research boundary, and the polymarket_* family plus bet_research all target prediction-market analysis. An agent would frequently struggle to pick the correct tool among these near-duplicates.
All names are snake_case, but the verb/noun style is inconsistent: get_* for flight lookups, ask_* for queries, noun-style names like entity_profile and bet_research, and the polymarket_* prefix group. Some subgroups are internally consistent, but there is no single predictable pattern across the set.
36 tools is far too many for a server named 'flights' — only 5 tools actually relate to aviation, while the rest span prediction markets, SEC/FDA data, npm packages, memory, and feedback. Even viewed as a general data platform, the count is heavy and the scope is unfocused.
For a flights server, the surface is severely incomplete: no scheduled flight status, delays, cancellations, or airport schedules — only live ADS-B snapshots. For the broader data-research domain the tools imply, coverage is better but still scattered, with no coherent lifecycle and several one-off utilities that don't connect to the rest.