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

Annotations declare destructive and non-idempotent, but the description goes well beyond them: pre-write validation ordering, the exact error codes (INVALID_INPUT, STATE_CONFLICT, NO_TABLE_KEY, CONFLICT), the 1024-byte and lone-surrogate limits, and the fact that a table without a key refuses upsert. This is unusually rich operational detail for a write tool.

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?

Front-loaded with the action and the bound, then layered with constraints in a logical order (validation → conflicts → upsert → alternative). It is dense and slightly run-on in the error-code sentence, but every clause carries information an agent needs.

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 destructive multi-row write with an output schema, the description covers limits, conflict and validation outcomes, the upsert path, and the refusal cases. Nothing an agent needs to call it safely is missing; return shape is delegated to the output schema as intended.

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, but the description adds genuine semantics the schema cannot express: key equality is exact-text based ('100' vs '100.0', number 1 vs string '1'), and upsert matches on the table's single unique column. The rows/expectedRevision relationship 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?

The first sentence gives a specific verb and resource with a hard bound: 'Append up to 1000 typed JSON rows', plus the return value ('every row ID'). It distinguishes append from update via the upsert note, but never names the sibling table_update_row, so the differentiation is implied rather than stated.

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?

It routes between the two modes ('To update stored rows instead, pass upsert: true') and tells the agent to prefer this tool over rewriting a file for additive changes. It lacks explicit when-not guidance (e.g., when to use table_update_row or table_get_rows instead), so it stops short of a 5.

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