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

Beyond the annotations (readOnly/openWorld/idempotent/non-destructive), the description discloses metering and cost behavior ('an empty page bills nothing and one `change` unit is metered per event returned'), a free-tier freshness floor, and the bounded-`limit` constraint that forces cursor pagination. These are operational traits the annotations cannot express.

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?

Front-loaded with the disambiguating 'change feed, not a search' clause, then sequencing cursor semantics, cost, filtering, pagination, and the sibling relationship. Every sentence earns its place, though the backtick-dense phrasing is slightly packed for a single paragraph.

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 still names the key return fields (`next_cursor`, the event stream) and covers billing, freshness, ordering, and pagination. The remaining gaps are the shape of the event payload and the role of `idempotency_key` on a read-only tool.

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 load and does so for most parameters: `since` semantics (strictly greater-than, ascending order), `limit` being bounded and not to be raised, and the two filter params (`company_id`, one exact `event_type`). It leaves `idempotency_key` and the deprecated `plane_api_key` (covered in-schema) unaddressed, so it is strong but not exhaustive.

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 — a ledger-style change feed keyed on `event_seq > since`, ascending, returned with `next_cursor` — and explicitly frames it as 'not a search', which separates it from the search_* siblings. It also names `watch_company` as the push-based twin. An agent can distinguish this from every sibling without opening a 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 and when-not-to-use guidance: replay with `next_cursor` instead of polling or re-searching, page with the cursor rather than raising `limit`, filter by `company_id` or a single exact `event_type`, and use `watch_company` when push/webhook is wanted. Alternatives and the conditions selecting them are spelled out.

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