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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false), the description adds valuable behavioral context: wildcard matching behavior, the need to verify recipient identity, and the interpretation of award amounts as federal obligations. This enriches the agent's understanding of how the tool behaves and how to interpret results without contradicting the annotations.

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 concise and well-structured: the first sentence clearly defines the tool's purpose, and the second provides critical cautions. No word is wasted, and all information is relevant and front-loaded.

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?

The tool has 3 parameters, no output schema, and annotations that clarify safety. The description covers purpose, usage, and data interpretation, which is sufficient for most use cases. It could be more complete by describing the output format (e.g., rows vs. aggregated statistics) or whether it returns all years or only matching ones, but the given information is adequate given the annotations.

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 low (33%), so the description must compensate. It adds wildcard matching semantics for the organization parameter and implies fiscal year parameters are used for filtering, but it does not clarify whether the fiscal years are inclusive, required, or how they interact. The description partially compensates but leaves gaps for the fiscal year parameters.

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 that the tool summarizes an organization's NIH SBIR/STTR award portfolio, specifying the grouping dimensions (core project, fiscal year, activity code, PI) and the target organization. This specific verb+resource+scope distinguishes it from sibling tools like nih_grant_award_history or search_grants, which focus on different aspects of NIH funding data.

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 provides clear context on when to use the tool (to summarize a specific organization's SBIR/STTR portfolio) and includes important cautions: wildcard-based matching necessitates recipient identity verification, and reported amounts are federal obligations, not revenue. It does not explicitly name alternative tools or state when not to use it, but the context and cautions offer practical guidance.

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