update_existing_record

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

Goes beyond the annotations by disclosing the ETag default (reads current record ETag when the table supports concurrency), the fail-closed behavior on unsupported concurrency, and the no-upsert boundary. Given destructiveHint=true and idempotentHint=false are already declared, the remaining gap is only what a successful response returns.

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?

Three tight sentences, no filler, with the concurrency guarantee front-loaded. Slightly dense jargon ('fresh ETag', 'native record') costs a little immediate readability, but nothing is wasted.

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 10-parameter mutation tool with no output schema, the description covers the safety-critical behavior that matters before invoking: concurrency protection, fail-closed default, and non-upsert semantics, while the schema carries parameter detail.

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 90%, so if_match, allow_unprotected_write, and dry_run are already documented in the schema; the description only restates the ETag default and the unprotected-write escape hatch in prose. With near-complete schema coverage, a baseline 3 is appropriate.

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?

States a specific verb and resource ('Update a native record') plus the concurrency scope ('row-version protection where supported'), and explicitly disclaims upsert behavior, which cleanly separates it from sibling upsert_record_by_key and create_new_record.

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?

Conveys implicit conditions – writes stop on unsupported concurrency unless allow_unprotected_write is explicit, and a missing GUID will not be created – but never states when to prefer this over siblings like upsert_record_by_key or delete_record_by_id, nor recommends a dry_run first.

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