Operator-only: retire a previously published named tool.
The catalog query itself is kept (still runnable via
execute_query_by_key); only its projected named tool is removed.
Reconnect to see it disappear from the tool list.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | ||
| npub | No | Required. The operator's npub (npub1...). | |
| dpop_token | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description discloses key behavioral traits: the catalog query persists, only the named tool is removed, and the change is visible after reconnection. It does not cover all edge cases (e.g., republishing), but sufficiently informs the agent of the primary 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?
The description is extremely concise (two sentences) with the key purpose and constraint front-loaded. Every word adds value without redundancy.
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?
While the description is brief, it covers the essential behavior of the tool. Given the presence of an output schema (not shown), return values are implicitly addressed, but the description could mention prerequisites or error cases. Still, it is fairly complete for a specialized operator tool.
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 only 33%, and the description adds no information about parameters. The 'key' parameter is undocumented, and the description does not clarify its purpose or format beyond the schema's minimal entry.
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 ('retire a previously published named tool') and the resource (named tool), and distinguishes it from the similar 'publish_tool' sibling by specifying it removes only the projected tool, not the underlying query.
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?
The description specifies 'Operator-only' as a usage constraint but does not explicitly mention when not to use this tool or provide alternatives (e.g., 'publish_tool' for creation). The guidance is implicit but lacks comparative 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.
The set is heavily clustered: audit_why_exists, explain_capability, suggest_capability_why, and authorize_capability_why all answer the same basic 'why does this capability exist?' question and differ mainly in provenance/authority. Many status and provenance tools (adoption_status, session_status, service_status, issue_provenance, pr_provenance, symbol_provenance, service_provenance) also blur together without close reading.
The overwhelming majority of tools follow a predictable cypher_verb_noun pattern in snake_case, which provides strong naming consistency across a very large surface. Minor deviations such as cypher_oracle_about, cypher_oracle_how_to_join, cypher_which_service_handles, and cypher_what_realizes_capability are noticeable but do not break the overall pattern.
112 tools is an extreme count for a single MCP server, regardless of how well the clusters are named; it heavily burdens tool selection, context, and agent discovery. The set spans unrelated domains including payments, coupons, credentials, provenance, issues, patents, queries, pricing, and NOS transformations, which should be split into separate focused servers.
Many domain clusters have strong lifeycle coverage: COUPs have mint/list/update/delete/redeem, credentials have courier delivery/box status/update/delete/forget, and the named-query catalog has full CRUD plus published-tool management. Minor gaps exist—e.g., no generic list_services, no delete for capabilities, and no close/resolve action for issues—but most flows have no outright dead end.