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

Annotations already flag readOnly=false, destructive=true, openWorld=false. The description adds value beyond them: it warns that changing the mapping alters what the recorded number means, and discloses a `needs_confirmation` return path. It does not detail reversibility, approval semantics, or permission requirements, so it is not complete.

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 tight sentences, front-loaded with the action and its scope, then trigger conditions and caveats. The 'say what you're changing and why' line is a soft instruction rather than voidless, but overall it earns its length.

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, nested-schema mutation with 10 params and no output schema, the description covers the trigger and the confirmation return, which is genuinely useful. It nonetheless leaves most parameter meanings and the full behavioral contract (reversibility, approval flow) underspecified.

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 only 30% across 10 params, so the description must compensate. It maps concepts to a few params (arguments→toolArgs, mapping→mapping, cadence→schedule, pause→enabled), but leaves label, workspace, approvalId, toolName, and windowHours unexplained. Partial compensation justifies the baseline 3, not more.

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 (change) and narrows the resource to a feed's arguments, mapping, cadence, or pause state. This cleanly separates it from siblings like ledger_feeds_create, ledger_feeds_run, ledger_feeds_delete, and ledger_feeds_list 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 an explicit trigger — reach for this when a feed's last run reports `empty` or `error` — and even diagnoses the `empty` cause (response shape moved). It stops short of naming alternative siblings (e.g. when to preview vs. run vs. recreate), so it is strong context without full when-not guidance.

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