update_row

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

With no annotations, the description carries the full burden and does substantial work: it declares the operation a WRITE, discloses that before/after values are audited, states that omitted fields survive, and explains the optimistic-concurrency rejection of stale edits. It does not describe what happens on a missing id or a failed write, which keeps it below a 5.

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 short sentences, front-loaded with the 'WRITE:' marker so the mutation nature registers immediately, and every sentence adds a distinct fact (mutation, audit, partial update, concurrency, backup caution). Nothing is padded.

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?

An output schema exists so return values need not be described, and the mutation semantics are well covered. For a 5-parameter tool with a nested data object and zero annotation coverage, though, the unexplained reveal flag and unspecified error behavior leave the definition incomplete.

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 0%, so the description must supply meaning, and it does explain data (supplied fields only) and expected_updated_at (stale-edit rejection). But the reveal parameter is never mentioned and its purpose is opaque, and the nested data object's accepted shape is not characterized, leaving a real gap.

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 'WRITE: update supplied fields' opening names a specific verb and resource, and 'omitted fields survive' pins down partial-update semantics, which distinguishes it from insert_row and delete_row in the sibling list. It stops just short of explicitly naming a sibling, so a 4 rather than a 5.

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?

'Optional expected_updated_at rejects stale edits' tells the agent when to supply that parameter, and 'Back up before overwriting useful data' implies a caution regime. However, there is no explicit statement of when to prefer this over insert_row, nor any prerequisites (auth, table existence), so usage is only implied.

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