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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the description is not responsible for basic safety disclosure. It adds useful behavioral context beyond annotations: data provenance from SBA's SBIR.gov records, the award-year counting semantics, and the side effect of open_topics querying SAM.gov and Grants.gov. It does not discuss pagination, rate limits, or freshness beyond the source caveat, but the key operational semantics are present.

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 front-loaded with the resource and scope, and every major clause—returned dimensions, filter list, open_topics behavior, and the run_plan caveat—contributes useful information. It is a dense paragraph rather than a crisply structured list, and the filter enumeration partly duplicates the schema, which keeps it from a 5.

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?

There is no output schema, so the description must explain return values; it does so comprehensively by naming totals, awards by year and phase, agency breakdowns, top companies, and the fields of latest awards. All eight parameters are accounted for, the open_topics behavior is described, and the counting caveat versus run_plan is included. An agent has enough information to call this 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?

Schema description coverage is 100%, so the input schema already documents all eight parameters thoroughly, including examples and enums. The description restates the filter list and examples but does not add syntax or meaning beyond what the schema provides, such as expected formats for combined filters or default behavior. The baseline of 3 is appropriate when the schema carries this much weight.

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: searching SBIR/STTR awards since 1983 and who received them. It enumerates the returned dimensions (totals, awards by year/agency, top companies, latest awards) so the agent knows exactly what this tool produces. It also distinguishes itself from the USAspending-based run_plan tool, making selection between them possible without opening schemas.

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 clearly explains the filters and adds the crucial caveat that SBIR.gov counts awards by award year while run_plan counts money by fiscal year, so the two differ. That gives strong context for when this tool is appropriate versus run_plan. It stops short of explicitly saying when not to use this tool, so it is not a full when/when-not/alternatives statement.

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