update_record

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

With no annotations, the description carries full behavioral burden and delivers: it discloses the REVIEW_REQUIRED result, shallow-merge semantics (omitted keys remain, null is stored), the need for the retrieved version, and the VERSION_CONFLICT retry prohibition. This is substantive, non-obvious behavior.

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 dense sentences, each earning its place: the legacy warning is front-loaded, merge semantics follow, and conflict guidance closes. No fluff or repetition of the schema.

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?

Covers the essential behavioral traps, version requirements, and the preferred alternative. With an output schema present, not detailing return values is acceptable; a minor gap is not explaining what to do with REVIEW_REQUIRED or when this tool is still appropriate.

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 must compensate for all three parameters. It does well for changes (shallow-merge top-level fields, null behavior) and expected_version (supply retrieved version, conflict handling), though record_id is left to the schema.

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 action ('direct write') on record data and explicitly contrasts with the preferred sibling flow (prepare_write/commit_write). It also describes the shallow-merge behavior, making the tool's function unmistakable beyond its name.

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?

Explicitly directs agents to use prepare_write/commit_write instead, signaling that this is a legacy path. It does not spell out any specific scenario where update_record should be chosen over its siblings, but the exclusion is clear enough.

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