create_record

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already communicate that this is a mutating, non-idempotent write operation (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds the scoping detail that creating a record requires prior schema discovery, which is useful. However, it does not disclose potential side effects such as triggering workflows, required permissions, or duplicate-check behavior, but the annotations cover the core safety profile.

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 two sentences: the first states the core action, the second gives a critical prerequisite workflow. Every clause earns its place, and the guidance is front-loaded before the advisory sentence. No filler or redundant restatement of the title.

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 two-parameter tool with full schema coverage and annotations indicating mutating behavior, the description provides the essential missing context: how to correctly determine payload fields. It also routes the agent to a sibling tool, describe_object, which closes the main knowledge gap. It could briefly mention that responses include the new record ID, but the absence of an output schema reduces that burden.

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 both parameters include clear descriptions with examples (object API name and field-values map). The description adds the workflow context of needing required fields and valid picklists, which complements rather than duplicates the schema. It does not need to restate parameter meanings because the schema already carries them.

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 opens with a specific verb-resource pair ('Create a new Salesforce record'), immediately distinguishing this tool from siblings like get_record, update_record, and delete_record. It also names the exact API domain (Salesforce) and pairs with a supporting sibling, describe_object, so an agent can tell what this tool is for at a glance.

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 explicitly instructs the agent to call describe_object first to determine required fields and valid picklist values. This is a concrete, actionable usage guideline that prevents errors and clearly differentiates the workflow from simply guessing at field names. It also implicitly warns that this is a create operation, not an update or upsert.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.