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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantive behavior beyond them: the match_strategy surface ('rcdc' vs 'text'), the measured 50% RCDC-density threshold that forces the text fallback, provenance.rcdc_window_coverage, and the de-duplication rule that each grant is counted once. It also flags that results are not paginated, which the annotations do not convey.

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 trigger condition and examples are front-loaded, followed by the response-surface explanation and then constraints, which is a sensible order. The prose is dense and every sentence carries information, though the parenthetical density explanation could be tightened.

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 two-surface cross-tab tool with an output schema already defining return values, the description supplies everything else an agent needs: required params, character and fiscal-year bounds, the surface-selection rule, provenance semantics, de-duplication, and the no-pagination fact. Nothing material is left to inference.

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 description coverage is 0%, so the description carries the load and does: both ic and query are required at 2-64 characters, fiscal years span 1985-2100 with start <= end, and ic='ALL' is a valid sentinel. match_strategy's 'auto' default and its allowed values are only partly explained (the 'rcdc'/'text' surfaces are described but 'auto' selection logic is not).

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 states a specific verb and resource ('what ONE NIH Institute funds in a topic') with concrete example queries, so an agent immediately knows this is an IC-by-topic cross-tab rather than a trend or search tool. It never names a sibling (topic_trend, funding_trend) to contrast against, which is the only thing keeping it from a 5.

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?

It gives explicit trigger conditions with quoted user phrasings ('what is NCI spending on immunotherapy', 'compare NIAID and NCI on vaccines') and tells the agent to call it once per Institute for comparisons. It also implicitly routes away from itself when a trend is needed, but no alternative tool is named for that case, so there is no true when-not guidance.

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