usa_spending_by_award

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

Annotations already cover read-only, non-destructive, and idempotent behavior, so the description's added value is the award type codes (A,B,C,D etc.) and the distinction between named groups and codes. This is beyond what annotations provide and helps the agent construct accurate queries. No contradictions with 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 two paragraphs: the first states the core purpose and filters, the second explains award type codes. It is efficient with no fluff, though the second paragraph could be structured as a list for readability. Overall, it is concise and front-loaded with the primary purpose.

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 tool with 12 optional parameters and no output schema, the description covers the main use cases and filter options. It doesn't explicitly mention the return format (e.g., fields like award amount, recipient name), but that is somewhat implied by the tool name and filter descriptions. The lack of explicit return details is a minor gap, but the description is sufficient for an agent to start using the tool correctly.

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 schema has 100% description coverage for all 12 parameters, so the baseline is 3. However, the description adds the mapping from award type names to internal codes (e.g., '02,03,04,05' for grants), which is not present in the schema's enum. This extra semantic information compensates and pushes the score to 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 clearly states the tool searches federal spending awards and lists the major filters (keyword, agency, recipient, date range, award type, amount). The phrase 'awards (contracts, grants, loans, direct payments)' is specific and distinguishes it from sibling tools like usa_spending_by_agency or usa_spending_by_state, which aggregate rather than return individual awards.

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 lists the filterable dimensions, which implicitly tells the agent when to use this tool (when a granular award search is needed). It does not explicitly mention alternatives or when not to use it, but the context of sibling tools (by_agency, by_state, by_recipient) makes the purpose clear. A 4 because the context is provided but exclusions are not stated.

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