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

With no annotations present, the description carries the disclosure burden and does a good job: it explains auth-dependent behavior, the 10-event cap, and the presence of limit_applied/limit_max in the response. The only significant behavioral gap is the lack of explanation for the dry_run parameter and any side-effect profile, though the read-oriented phrasing mitigates this.

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 three tight sentences with the core definition front-loaded before the mode-specific details. Every sentence carries distinct information and there is no filler.

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 read-only change-feed tool, the description covers the essential invocation modes, the endpoint, and key response fields despite the absence of an output schema. Minor omissions—dry_run semantics and cursor format—prevent full completeness, but an agent can still invoke the tool correctly in either mode.

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 0%, so the description must compensate. It adds meaning for since (cursor), api_key (switches between modes), and slug (path parameter in the feed endpoint), but it does not explain dry_run or the expected cursor format/type. This partial compensation merits a mid-range score.

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 clearly identifies a specific operation: fetching change events since a cursor, and further distinguishes anonymous preview behavior from authenticated subscription feed behavior. It references the concrete endpoint (GET /api/feeds/{slug}/changes), making an agent confident about what resource is being accessed.

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?

Usage context is clearly split into two cases: anonymous callers get a limited latest-day preview, while authenticated callers use an api_key to access their subscription feed. It does not explicitly list sibling alternatives or say when not to use the tool, so it falls short of a 5.

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