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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the bar is lower, and the description adds real behavioral context: delta dedup semantics (each change comes once), windowing, and API Pro gating for top-trader moves. It omits rate limits and return-shape details, but the output schema covers the latter.

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-loads the core delta concept and then layers the continuation rule and gating. A few trailing fragments ("Plus and API Pro. Research, not financial advice.") are minor but the whole paragraph stays tight and purposeful.

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 5-param read tool with an output schema and rich annotations, the description covers the essentials: delta semantics, continuation, and availability tiers. The remaining gap is undocumented params like `ids` and `cursor`, which neither schema nor description fully explain.

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?

With 40% schema description coverage, the description must compensate. It reinforces the `since` parameter (set to the answer's `until`) and maps the change categories that `types` filters on, but `ids`, `cursor`, and `segment` get no mention in the description, leaving gaps the schema only partly fills.

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 and resource — only what changed since your last call, newest first — and enumerates the change classes (headlines, analyst views, price moves, new/closing markets, top-trader moves). This clearly distinguishes it from kellian_get_context, which returns full state rather than a delta.

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 an explicit continuation protocol ("Call again with since = the answer's until") and explains that each change appears once in the window after it was recorded, which is clear context for polling. It stops short of explicitly saying when to prefer this over kellian_get_context, so no hard exclusions are stated.

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