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

Annotations already indicate read-only, idempotent, open-world. The description adds important context beyond annotations: billing ('empty page bills nothing', 'one change unit is metered per event returned'), event ordering, cursor mechanics, and free-tier freshness behavior. No contradictions.

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?

Every sentence adds information: purpose, cursor usage, billing, filters, limit, free-tier, sibling relationship. The most critical scoping and usage info is front-loaded. Slightly dense, but no wasted words.

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?

With no output schema, the description covers the main concerns: cursor, billing, filters, and push/pull distinction. It does not specify the structure of each event object beyond naming event types, and idempotency_key remains undocumented, but the operational behavior is fully covered.

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 description coverage is only 17%, so the description carries the burden. It clarifies `since` (event_seq > since), `limit` is bounded, and filters by `company_id` or one exact `event_type`. However, `idempotency_key` is not addressed in the description, leaving that param semantically unexplained.

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?

Description opens with a precise definition: 'The change feed, not a search: ledger events ... with event_seq > since, ascending, plus next_cursor.' It identifies the resource (ledger events) and the operation (change feed retrieval), and explicitly distinguishes itself from a search and from watch_company. This clearly separates it from sibling tools.

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?

Provides explicit guidance: 'Replay with next_cursor instead of polling or re-searching' and 'limit is bounded -- page with the cursor rather than raising it.' It names the alternative watch_company for push-based delivery via webhook, so an agent knows when to choose this pull-based tool.

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