Append rows

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

Annotations only flag readOnlyHint: false and idempotentHint: false, but the description goes far beyond them: it warns that re-appending duplicates rows, explains what happens with INSERT_ROWS vs OVERWRITE (data shifts vs writes into free rows), and documents that the response's updates.updatedRange reveals where rows landed. This is exactly the behavioral context that the flat annotation flags cannot convey. No contradiction with annotations.

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 dense sentences, all carrying operational value: purpose+mechanism, response behavior, option semantics, and the retry warning. The core purpose is front-loaded and the retry guidance earns its place as critical safety information. Slightly long, but there is no filler or repetition of schema content.

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?

Complete for a 5-param mutation tool with no output schema: it covers the append mechanism, the return field (updates.updatedRange) since no output schema exists, option semantics, and the retry safety path. The only minor gap is that the alternative write_values is never explicitly named for choosing the right tool in the first place.

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 baseline is 3, but the description adds real value on top: concrete range format examples ('Sheet1!A1:D1' or just 'Sheet1') clarify how the table region is specified, and it explains the behavioral difference between INSERT_ROWS and OVERWRITE beyond the enum labels. The values and spreadsheet_id params are already well-handled by 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 description states a specific verb+resource combo ('Appends rows after the last row of the data table') and explains the distinguishing mechanism — the API finds the first free row from a table region. This clearly separates it from write_values (targeted range) and batch_write_values without needing to open either sibling's schema.

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?

The description gives explicit guidance for the retry case: 'Never retried after an ambiguous failure... check the sheet first (read_values) before re-sending,' naming the exact alternative tool and the condition for using it. It explains insert_data_option behavior, but it never explicitly contrasts append_values with write_values for the normal case — the 'finds the first free row itself' mechanism implies it, but the sibling distinction isn't made explicit.

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