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. The description adds that the tool deletes memories saved earlier, which is consistent but doesn't provide additional behavioral context like behavior on missing keys or side effects.
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. The purpose is stated first, followed by usage guidance. Every word serves a purpose.
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-parameter tool with no output schema, the description is mostly complete. However, it does not mention behavior when the key does not exist (though idempotentHint implies safe operation). An additional sentence about expected behavior for missing keys would make it fully complete.
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?
The input schema covers 100% of parameters, describing 'key' as 'Memory key to delete'. The description adds no further semantic detail beyond what is already in the schema, meeting the baseline.
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 clearly states the action ('delete'), the resource ('previously stored memory'), and the means ('by key'). It distinguishes from sibling tools 'remember' and 'recall' by explicitly pairing with them.
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 scenarios (stale context, task completion, clearing sensitive data) and suggests pairing with 'remember' and 'recall', giving clear guidance on when and with what alternatives 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.
Several tools appear to do the same thing at the top level: ask_pipeworx, ask_pipeworx_beta (explicitly identical today), and ask_pipeworx_grounded are near-duplicate routing entry points, and deep_research overlaps heavily with them. Among the ct_* tools, ct_count_by_condition, ct_competitive_landscape, ct_sponsor_pipeline, and ct_compare_sponsors all provide overlapping counting/landscape functionality, making correct selection genuinely ambiguous.
The overwhelming majority of tools use lowercase snake_case and mostly follow a verb_noun or domain-prefixed pattern (ct_search, ct_get_study, list_subscriptions, validate_claim, resolove_entity). Some names are noun phrases rather than verbs (ct_competitive_landscape, entity_profile, polymarket_edge_tracker) but the overall style is consistent and readable, with only minor deviations.
44 tools is far too many for a server named 'Clinicaltrials'; only 13 tools are actually clinical-trials-specific while the rest span general data lookup, prediction markets, memory, subscriptions, and npm scanning. The count is inflated by redundant entry points (ask_pipeworx/beta/grounded) and overlapping ct tools, making the set feel heavy and unfocused.
For the clinical-trials registry domain, the surface is largely complete: search, full study details, results summaries, condition counts, sponsor pipelines, location-based lookup, recent updates, and catalyst tracking are all represented. Minor gaps exist (e.g., historical versions/protocol amendments and advanced filter combinations), but most could be worked around via the universal ask_pipeworx router.