sf_delete_recordDelete a Salesforce record by ID. Specify object type and record ID. Returns success status.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Salesforce record ID | |
| object | Yes | SObject type (e.g., "Account") |
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | Error code if deletion failed | |
| message | No | Error message if deletion failed | |
| success | No | Whether record was deleted successfully |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, so the description's mention of 'Delete' is consistent. It adds 'Returns success status,' which is useful but minimal. No contradiction.
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?
Single sentence, 12 words, no unnecessary information. Efficiently communicates the core action.
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 delete operation with full annotations and output schema, the description is complete. It covers action, parameters, and return type sufficiently.
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%, so the description's mention of 'ID' and 'object type' aligns with schema but adds no additional meaning beyond the parameter names.
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 it deletes a Salesforce record by ID, specifying the action and resource. It is specific but does not differentiate from sibling tools like sf_update_record, which also uses IDs.
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?
No guidance on when to use this tool versus alternatives (e.g., sf_update_record for soft delete, sf_query for retrieval). The description is too brief to convey context for selection.
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 mixes Salesforce CRUD tools with a large Pipeworx research and prediction-market platform, and several tools overlap heavily: ask_pipeworx vs ask_pipeworx_beta are functionally identical, grounded/validate_claim/deep_research cover similar lookup/verification territory, and the six polymarket/bet tools share edge-finding purposes with only subtle distinctions. An agent would need to read long descriptions carefully to pick the right one, so misselection risk is high.
Salesforce tools follow a clear sf_verb_noun pattern, and the Pipeworx tools mostly use lowercase snake_case phrase names, but the conventions diverge: ask_pipeworx has no underscore, deep_research/entity_profile are noun phrases rather than verb-first, and the sf_* prefix is a separate naming family. It is still readable, but it is not a single predictable pattern.
39 tools is well past the heavy threshold, and most belong to a broad data/research platform rather than the Salesforce scope implied by the server name; only 8 tools are actually Salesforce CRUD/query operations. The count feels bloated for a coherent assistant, even if individual features are useful.
The Salesforce subset is complete: create/get/update/delete/query/search/describe/list-object cover the record lifecycle with no dead ends. The broader Pipeworx ecosystem also has strong coverage, including routing, grounded verification, research, entity resolution, memory, and subscriptions, with only minor gaps such as no direct citation-fetch tool and no Salesforce upsert/bulk operations.