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 indicate destructiveHint=true and readOnlyHint=false. Description adds context about clearing sensitive data, enhancing transparency beyond annotations. No contradiction.
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, front-loaded with action ('Delete a previously stored memory by key'), no unnecessary words. Efficient and well-structured.
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 tool with one parameter, no output schema, and comprehensive annotations, the description covers all necessary context effectively.
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%, so schema fully documents the 'key' parameter. Description does not add further semantics beyond what is in the schema, meeting baseline but not exceeding.
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 the tool deletes a memory by key, using verb 'delete' and resource 'memory'. It distinguishes from siblings 'remember' and 'recall' which store and retrieve 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?
Explicitly lists when to use: stale context, task completion, clearing sensitive data. Also suggests pairing with 'remember' and 'recall', providing guidance on alternatives.
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 have unclear boundaries: ask_pipeworx_beta is explicitly identical to ask_pipeworx right now, and ask_pipeworx_grounded is a subtle behavioral variant, creating a real selection hazard. The six polymarket_* tools also blur together (edges vs arbitrage vs fill_risk vs kalshi_spread all relate to finding and acting on mispricings), and scan_competitor_ai_presence is largely a wrapper over ai_visibility_check.
All names are snake_case and several families share clear prefixes (ask_pipeworx, polymarket_*, pipeworx_*, scan_*), which keeps the set readable. However, the set mixes verb-first names (get_sample, compare_entities, resolve_entity) with noun-first names (entity_profile, bet_research, recent_changes, polymarket_edges), and the _beta suffix signals a status while _grounded signals a behavior, so the pattern is not predictable.
33 tools is above the threshold where a tool set starts to feel bloated, and for a server named 'Biosamples' it is an extreme scope mismatch: 31 of 33 tools relate to Pipeworx data routing, prediction markets, memory, or subscriptions rather than biological samples. The count is also padded with near-duplicates such as ask_pipeworx_beta and scan_competitor_ai_presence.
Against the server's stated identity, the BioSamples surface is severely thin: only search_samples and get_sample exist, with no batch retrieval, project/group navigation, sample-group hierarchy, or submission/update path. The 31 unrelated tools do not fill this gap — they serve a completely different domain, so an agent using this server for biological sample data will hit dead ends.