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

Annotations only declare the safety profile (readOnly=false, idempotent=false, destructive=false, openWorld=false), so the description carries the real burden and does: no run is started, the schedule is HELD rather than applied when the recipe cannot refresh, lock freezes platform adjustment, expected_version causes a conflict refusal rather than an overwrite, and rationale is kept verbatim. It even discloses the return shape. No contradiction with destructiveHint=false, since resetting a table is explicitly what this tool avoids.

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 is front-loaded and most sentences carry distinct operational information (held schedules, floor refusal, lock, version guard). It is dense and unusually long, with a few clauses that could be tightened, but almost nothing is purely redundant.

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 complex mutation tool with no output schema and undocumented parameters, the description covers purpose, prerequisites, conflict handling, refusal modes, the held-schedule edge case, and even the returned fields. An agent has everything needed to call it correctly and interpret the result.

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?

With 0% schema description coverage the description must compensate, and it explains cron (five fields, UTC), interval_seconds (counts from now), rationale (verbatim), lock (freezes adjustment), and expected_version (from get_table). However, the 'timezone' parameter is never mentioned and 'evaluated in UTC' arguably conflicts with its existence, leaving a small gap for a 7-parameter tool.

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?

Opens with a specific verb and resource: 'Sets a live table's refresh schedule, or replaces the one it has, without starting a run or fetching anything.' It immediately distinguishes itself from start_run, promote_table, and demote_table by stating what it does not do, so an agent can identify it without opening the 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?

Explicit about when to use it (a live table with no schedule, 'get_table shows schedule null'), when not to act (schedule HELD when recipe cannot refresh — report and do not call again), the alternative it replaces (demote+promote that resets the table), and refusal conditions (non-live table, cadence below the floor). Names get_table as the prerequisite read.

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