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 signal destructiveHint=true and idempotentHint=true. Description adds context about sensitive data but no new behavioral traits beyond 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: first defines purpose, second gives usage guidance. 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?
For a 1-param destructive tool with no output schema, the description fully covers what, when, and pairs. No gaps.
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 schema already describes the 'key' parameter. Description only says 'by key' which adds no additional meaning beyond schema.
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 starts with 'Delete a previously stored memory by key' which is a specific verb+resource+mechanism. It distinguishes from siblings by naming 'remember and recall' as paired tools.
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 states when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Pairs with remember and recall, implying alternatives. Lacks explicit 'when not to 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.
Most tools have clearly distinct purposes with detailed routing guidance, but the three ask_pipeworx variants and overlapping company-focused tools (entity_profile vs compare_entities vs recent_changes) create some ambiguity. The descriptions are thorough enough that an agent can usually select correctly.
All names are snake_case and mostly descriptive, but they mix verb-first (ask_pipeworx, discover_tools), noun-first (entity_profile, gold_price), and domain-prefixed (polymarket_*, pipeworx_*) patterns. The style is consistent enough to be predictable, though not uniform verb_noun.
34 tools is well past the 25-tool threshold for "too many," and the server name (Nbp Pl) suggests a narrow Polish-bank scope while most tools cover unrelated domains like prediction markets, dependency scanning, and AI visibility. The breadth makes the set feel over-stuffed and unfocused.
The toolset covers a remarkably complete data-research workflow: general querying, grounded answers, deep research, entity resolution, profiles, comparisons, claim validation, change feeds, discovery, subscriptions, and memory. Minor gaps like subscription updating or a direct source catalog exist, but agents can work around them.