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, idempotentHint=true. Description adds no extra behavioral context like error handling or idempotency behavior.
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: first states purpose, second gives usage guidance. No unnecessary words.
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 1-param tool with no output schema, description covers purpose and usage. Could mention return value or error case, but not critical.
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%. Description only mentions 'by key', adding no extra meaning beyond the schema's description.
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 verb 'delete' and resource 'memory by key'. Explicitly distinguishes from siblings 'remember' and 'recall'.
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?
Provides clear when-to-use scenarios: stale context, task done, clear sensitive data. References related tools. Lacks explicit when-not-to-use, but adequate.
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 tool clusters overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all route research questions; polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, and bet_research all hunt prediction-market edges; ai_visibility_check and scan_competitor_ai_presence do nearly the same job. The verbose descriptions help, but an agent would still struggle to pick the right tool in these clusters.
Everything is snake_case, but there is no coherent pattern: some names are verb_noun (compare_entities, validate_claim), some are bare verbs (remember, forget, recall), some are prefixed by domain (eodhd_*, pipeworx_*, polymarket_*, ai_visibility_*), and the Eodhd prefix clashes with the Pipeworx family. The conventions feel inherited from multiple unrelated codebases rather than a unified design.
33 tools is already heavy for most servers, but the real problem is that only 2 tools (eodhd_eod_prices, eodhd_fundamentals) relate to the server's stated purpose. The other 31 span Pipeworx research, Polymarket betting, memory, subscriptions, feedback, llms.txt generation, and npm dependency checking — a massively over-scoped grab bag for a server named 'Eodhd'.
For the nominal EODHD domain the surface is severely incomplete: no splits, dividends, options, exchanges list, or other standard EODHD endpoints — just prices and fundamentals. As a general research/data platform it is broad rather than deep, mixing a decent question-answering core with unrelated one-off utilities, so no single coherent lifecycle is fully covered.