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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that — cursor-based incrementality, a developer-tier requirement, and a fixed training-set sample for free evaluation — but it names the returned token 'next_cursor' while the schema parameter is 'cursor', leaving the loop ambiguous, and says nothing about the shape of returned change records.

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 short sentences, front-loaded with what the feed contains before the polling mechanics. Dense and mostly waste-free, with a small cost from the next_cursor/cursor naming mismatch and the environment-specific 'Developer required' clause.

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 carries return-value burden; it partially discharges this by naming the four change kinds and the cursor to persist, but omits anything about the change record shape, ordering, or the league filter's effect on the feed.

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 the baseline is 3. The description reinforces the cursor round-trip but adds no meaning for limit or league, and it does not reference the required user_request parameter at all, which is the one argument an agent could most easily mishandle.

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?

The description names a specific resource and scope: a change feed covering new, changed, pulled and restored lines. The enumeration of event types distinguishes it from siblings such as get_line_history (full history) or get_stale_lines (stale-only), though it never names an alternative explicitly.

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 concrete operational guidance: save next_cursor and pass it back to read only what moved since, framed as 'the cheap way to stay current'. This implies the incremental-polling use case versus a full refetch, but no explicit when-not or named alternative is stated.

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