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

Annotations already flag destructive=true and idempotent=false; the description adds the parts annotations can't cover — the merge-vs-replace semantics, optimistic concurrency via expectedRevision (stale ⇒ CONFLICT), NOT_FOUND on unreadable rows, and a 'bounded receipt' return. It doesn't discuss reversibility or whether a conflicting retry should re-read first.

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?

Four tight sentences with the core operation first, then preconditions, then error taxonomy. Every sentence carries information, though the error-code clause is dense enough that an agent may need to re-read it.

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 shape needn't be spelled out, and the description still notes a bounded receipt. Combined with annotations, the description covers the write semantics, required preconditions, concurrency behavior, and failure modes an agent needs before calling a destructive mutation.

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 the baseline is 3; the description still adds meaning beyond it by tying rowId to the table name and by documenting key-column validation rules (object/array/over 1024 bytes/U+0000/lone surrogate ⇒ INVALID_INPUT) that appear nowhere in the schema. The 'why' and expectedWorkspaceRevision semantics largely restate 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 verb and resource ('Partially merge typed JSON into one table row') and pins the addressing model ('named by its own id (rowId names its table)'). That partial-merge framing implicitly separates it from table_append_rows and table_delete_rows, but no sibling is named explicitly.

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?

Gives concrete conditional guidance: 'A workspace table needs expectedRevision and why,' and notes expectedRevision is optional otherwise. It also routes the agent on error conditions. It stops short of naming an alternative tool or saying when not to use this one.

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