upsert_record

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

The description discloses mode-specific failure behaviors and PUT semantics, which is valuable given no annotations are present. But it does not mention permissions, idempotency beyond 'PUT semantics', or response contents. For a mutation tool with zero annotation support, this is moderate transparency.

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 concise, front-loaded, and free of fluff. It states the core purpose in one sentence and then explains all modes in a follow-up, with every clause contributing meaningful information.

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?

Given the tool's complexity (4 params, nested data object, no annotations, no output schema), the description covers main behavior and mode semantics thoroughly. The schema's data parameter already provides detailed field formatting guidance, so the description is sufficient for correct invocation, though it omits return values and auth prerequisites.

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 baseline is 3. The description adds value by clarifying the meaning of each mode (e.g., 'createOnly' fails if exists) beyond the schema's brief 'Upsert behavior' note. It also reinforces that recordId must be a GUID, aligning with the schema's uuid format.

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: 'Create or update a Dataverse record with a known GUID (PUT semantics).' This clearly distinguishes from sibling tools like create_record (no GUID needed) and update_record (requires existing record). It also explains the three modes, making the purpose unambiguous.

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 provides clear context: use with a known GUID, and explicitly explains when each mode is appropriate ('createOnly' fails if exists, 'updateOnly' fails if not). However, it does not directly name sibling tools as alternatives for non-GUID scenarios, so it lacks explicit exclusions.

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