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

Annotations already declare the operation safe/read-only, so the bar is lower, but the description goes well beyond by explaining cursor semantics, monotonic sequence numbers, delivery-id pitfalls, oldest-first ordering, pagination via next_seq, retention failure modes, and the fact that sequence numbers are not guaranteed dense. This is rich behavioral disclosure with no contradiction.

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?

The description is long but dense and every sentence earns its place. The central purpose is front-loaded, then critical gotchas (cursor misuse, retention, truncation, non-dense sequences) follow in logical order. There is no filler or repeated schema content.

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?

Despite having no output schema, the description covers the essential runtime contract: has_more, next_seq, truncated, and latest_seq are all explained, including how to compute an honest lag. The tool's complexity (pagination, retention, ordering, cursor semantics) is fully addressed, and the alternative path for unrecoverable data is provided.

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 100%, so baseline is 3, but the description adds substantial parameter-level meaning: since_seq is explained as the highest processed sequence, default 0 behavior is clarified, and pagination via passing next_seq back is explicit. It also warns against using delivery id as a cursor, which is exactly the kind of semantic nuance the schema cannot convey.

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 ('Re-read'), resource ('a webhook subscription's events'), and ordering ('in order from a cursor'), with a concrete user question it answers. It also explicitly contrasts itself with propline_get_webhook_deliveries, making sibling differentiation immediate.

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 context ('my endpoint was down, what did I miss?') and clearly names the alternative that should be used instead for debugging (propline_get_webhook_deliveries). It also instructs when to fall back to REST endpoints (on truncation), so an agent knows when not to rely on this tool.

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