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

Annotations only tell the agent this is a non-read-only, non-idempotent, open-world call. The description adds the material facts: it costs money per run, the first run covers all rows with data while later runs only process new rows, overwriting filled output cells is refused unless overwrite:true, a full re-run re-charges every row, and schedule creation itself is free. No contradiction with destructiveHint=false.

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?

The purpose and billing model are front-loaded, and nearly every sentence carries distinct information. It is a single dense paragraph with mild redundancy ('later runs only the rows added since' is restated later as 'later runs only fill rows added since'), which costs it the top score.

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 13-parameter mutation tool with no output schema, the description covers cost, cadence, watermark detection, column reuse, restrictions, and even names the two return fields (first_run_rows, first_run_estimated_cost_cents). An agent has enough to call it correctly without further discovery.

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 92%, so the baseline is 3, but the description earns an extra point by explaining semantics the schema does not: watermark_column must be a header that has a value on every data row, weekly uses days_of_week while monthly uses day_of_month, and reused_columns are reused rather than duplicated. It does not, however, detail input_columns or header_row usage.

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 states a specific verb and resource ('Schedule a Flow on a connected Google Sheet') and the rest scopes exactly what a schedule is: a paid run on a cadence. It is clearly distinct from run_flow, list_schedules, and delete_schedule in the sibling set.

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 when/when-not guidance and names the alternative: one schedule per tab means 'delete the first schedule with delete_schedule before creating another,' and it states exclusions (flows with required variables, gates that move or delete rows, and hosted lists cannot be scheduled). This is about as complete as usage guidance gets.

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