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

Annotations already establish read-only, non-destructive, closed-world behavior, so the description's job is to add operational context — and it does: result cap of 25, sort order by largest FY2025 obligation, inclusion of vendors, lists, rule status, and project end date, plus the fact that it is free to call. What it omits is filter combination semantics (AND vs OR) and whether there is any way to reach results beyond the top 25.

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?

One dense but well-ordered paragraph: purpose first, filter inventory second, return shape last. Every clause carries information, though the parenthetical value lists make it slightly run-on and the parenthetical vendor list ('...tp_link...') trails into the next clause.

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?

With no output schema, the description correctly takes on the burden of describing the return payload (totals, up to 25 awards, ordering, included fields). Combined with annotations covering the safety profile, the definition is nearly sufficient; the residual gaps are filter-combination logic and the missing in_force tier value.

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 has to carry parameter meaning and much of it does: it spells out the legitimate list values (BIOSECURE, 1260H, UFLPA, SEC889, FCC_COVERED), gives example vendor ids, and defines q as matching award number, recipient, or project title. However, agency and institution get no explanation at all, and the tier enumeration is incomplete — it lists likely_paid, narrow, broad but omits in_force, which is a valid enum value the agent would otherwise never consider.

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?

Opens with a specific verb and resource ('Search the Research Exposure Ledger's awards') and enumerates the filterable dimensions, so an agent knows exactly what this retrieves. It does not name a sibling tool to contrast against, so the differentiation from exposure_summary or exposure_institution is only implied by the word '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 filter list implies when the tool is appropriate (you have a list, vendor, agency, tier, institution, or free-text constraint), but there is no explicit when-to-use or when-not-to-use statement. Nothing tells the agent why it would pick this over exposure_summary or exposure_institution, both of which appear to overlap in subject matter.

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