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

Adds rich behavior beyond the slim annotations: it costs a full build, discard_snapshot_history is the consent a refused snapshot_history_would_be_discarded waits for, it replaces snapshot history with one day, and the return payload plus held/sample-first handoff to confirm_run/approve_full_run is described. The idempotency-key semantics reconcile with idempotentHint=false rather than contradicting it.

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?

Purpose and the escape-hatch condition are front-loaded, and the example is placed usefully. It is dense and runs long as one block, but nearly every clause carries operational information an agent needs; only minor tightening is possible.

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 5-param mutation with no output schema and no annotation coverage, the description supplies the return shape ({table_id, status, run_id, ...}), the confirm_run projections, the sample-first handoff, and the recovery guidance ('ask again with the same request_id'). Nothing an agent needs to call it correctly is missing.

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 compensate: it explains request_id (same key returns the same resync, omit for a new one), reuse_saved_answers:false (reads every per-row answer fresh) and discard_snapshot_history:true (consent to replace history). expected_version is only implied by the example, so one parameter is left semantically thin.

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+resource+scope: 'rereads every source of a live table as one progressive full run of its current recipe.' It explicitly distinguishes itself from the sibling refresh_table by naming it and its failure mode (incremental_unavailable). An agent can select it without opening any 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?

Gives explicit when-to-use conditions (refresh_table returned incremental_unavailable, or the person asked to rebuild from sources), an explicit when-not ('Only call it when the person asked for a full reread'), and names the alternative. Nothing is left to inference.

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