sf_upsert_record

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

There are no annotations, so the description must carry the behavioral burden. It does disclose the idempotent behavior and duplicate-free guarantee, which is valuable. However, it does not mention what happens on error, whether existing field values are overwritten, or any permission/response details.

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 brief and front-loaded: the first sentence states the core action, and the second adds the critical idempotency guarantee. Every sentence earns its place with no filler.

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?

With no annotations, no output schema, and 0% parameter schema coverage, this is incomplete for an agent to invoke reliably. It lacks information about return values, error cases, required field behavior on create, and what happens when the external ID matches multiple records.

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 0%, so the description would need to explain the parameters, but it only clarifies the external ID concept. It does not define sobject, fields, or the exact relationship between external_id_field and external_id_value well enough to fully compensate for the missing schema documentation.

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 uses a specific verb phrase 'Create or update a record identified by an external ID field,' clearly naming the resource and the identifying mechanism. It also distinguishes itself from the sibling tools sf_create_record and sf_update_record by combining both operations into an upsert.

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?

It gives clear usage context: the standard idempotent create-or-update integration pattern, and explicitly states it is safe to call repeatedly with the same external ID. It does not explicitly name alternative tools or exclusion cases, but the context is strong enough for an agent to infer when this tool is appropriate.

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