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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=true, so the description adds context about why to delete (sensitive data, stale task) without contradicting annotations. It doesn't reveal additional behavioral traits beyond what annotations convey, but the usage context is valuable.
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 concise sentences with no waste. Purpose, usage, and pairing are front-loaded. Every sentence serves a clear function.
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?
Given the tool's simplicity (one required param, no output schema), the description covers purpose, usage, and relationship to siblings completely. No gaps remain for effective tool selection.
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 description only repeats 'by key' without adding format or type details beyond the schema's 'Memory key to delete.' Baseline 3 is appropriate as schema already documents the single parameter adequately.
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 explicitly states 'Delete a previously stored memory by key,' which is a specific verb+resource combination. It distinguishes from sibling tools by mentioning pairing with 'remember' and 'recall,' making its role clear.
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 explicit usage conditions: 'when context is stale, the task is done, or you want to clear sensitive data.' Also advises pairing with 'remember and recall,' offering clear when-to-use and alternative context.
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 overlapping jobs: ask_pipeworx_beta is currently identical to ask_pipeworx, ask_pipeworx_grounded is the same router with stricter extraction, and discover_tools/suggest_questions both serve discovery. Company-facing tools also overlap (entity_profile vs recent_changes vs compare_entities), so an agent could easily route a query to the wrong tool despite detailed descriptions.
Names are mostly snake_case and grouped prefixes like get_*, ask_pipeworx*, and polymarket_* are readable. However, conventions are mixed across the set: some are verb_noun (search_companies), some are noun phrases (entity_profile, deep_research, recent_changes), and the Companies House family sits awkwardly beside unrelated Pipeworx and prediction-market families.
With 36 tools, the server is already heavy, but only five tools actually serve the named Companies House domain. The other 31 belong to Pipeworx querying, memory, subscriptions, and Polymarket trading, which is a severe mismatch between the server's stated purpose and its actual surface.
For UK company data, the core surface is mostly covered: search, company profile, filings, officers, and PSCs. However, charges and official document retrieval are missing even though get_company links to them, and the unrelated tools do nothing to complete the Companies House domain.