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

Annotations already indicate this is a read-only, open-world, idempotent, non-destructive operation. The description adds useful context about the data source (api.nsf.gov), the fact that no auth is needed, and that it returns an abstract excerpt for each match. This goes beyond the annotations and sets expectations about the returned data scope, though it doesn't describe pagination details.

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 a single, dense paragraph that is front-loaded with the primary purpose and filter criteria. It efficiently conveys the returned fields and data source without excessive verbosity. No wasted words; every sentence adds value.

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?

Given the tool is a straightforward search with 0 required parameters, the description fully covers the necessary information: what it searches, what it returns, and the data source. The output schema exists, so return value details are presumably documented elsewhere. The description is complete enough for an agent to decide to invoke it and know what to expect.

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?

The input schema already has a 100% description coverage, with each parameter having a clear description (e.g., date format, examples). The tool description does not add any semantic detail beyond what the schema provides, but it does reinforce the overall scope. Baseline 3 is appropriate because the schema does the heavy lifting.

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 states the tool searches NSF funded research awards, and lists all the filter criteria (keyword, institution, state, CFDA number, date range). It also specifies the returned fields, which distinguishes it from the sibling detail tool. The purpose is unambiguous and comprehensive.

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 lists all possible search dimensions, making it clear when to use this tool. It also mentions the data source and that no auth is required, which is useful context. While there's no explicit 'when not to use', the detail tool is named as a sibling for retrieving more detail on a specific award, so the differentiation is implicit.

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