Get Changes

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context: conditional portfolio block for keyed callers with saved sites, per-site verdict flips, excess-power deltas, alerts fired, and required caching of generated_at. No contradictions with annotations, and it discloses the tool's special 'PLUS' behavior beyond the schema.

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 one dense but front-loaded paragraph; it starts with the core purpose and then layers details. Every clause adds value (contents, portfolio, since syntax, caching, example), but it could be tightened slightly. It is not just a tautology—it's a rich, purposeful description.

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 an output schema present and strong annotations, the description still goes beyond the minimum: it covers the delta-fetch use case, parameter syntax, special keyed-caller behavior, and a caching protocol. Given the tool's moderate complexity, this is a complete, self-contained description that would guide an agent effectively.

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?

Both parameters are fully documented in the schema (100% coverage), so the baseline is 3. The description adds usage guidance by explaining the since parameter's role in delta sync and recommending caching generated_at, but it doesn't elaborate on limit beyond the schema's own description. This modest addition earns a 4.

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 opens with 'Incremental sync — what changed in DC Hub since a timestamp', providing a specific verb (sync) and resource (DC Hub) and clearly distinguishing it from siblings by emphasizing delta-only fetching. It enumerates concrete content types (DCPI movers, facilities, M&A deals, news, portfolio block), fully clarifying the tool's scope.

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?

The description explicitly frames the tool as a delta-fetch alternative: 'so an agent pulls only the delta instead of re-fetching everything'. It gives a usage pattern with caching guidance ('cache the response generated_at and pass it back next call') and a concrete example ('Try: get_changes since=7d'), making when-to-use clear. While it doesn't name sibling tools as alternatives, the 'instead of' effectively differentiates.

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