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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: the data source (USASpending.gov synced data), the cost ($0.02 USDC per call), and a concrete example output showing the type of insight returned. It does not mention pagination, rate limits, or exact response format, but the read-only nature needs little extra disclosure.

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 efficient: four sentences covering purpose, output, an illustrative example, source, and cost. Every sentence adds information, and the most important guidance (use cases and what is returned) is front-loaded. There is no redundant phrasing or filler.

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 has no output schema, the example provides a useful shape of expected results, and the description covers source, cost, and use cases. It does not mention whether additional filters are required or if vendor_name is the sole mandatory input, but that is already in the schema. Minor gaps like pagination or error handling are not critical for a simple query tool.

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 only 20% (state has a description; other parameters do not). The description compensates by listing the key filter dimensions (vendor, agency, NAICS code, fiscal year), mapping to four of the five parameters)Skip state entirely, but the main parameters used for federal revenue concentration are covered. This adds meaning beyond bare schema names, though it does not elaborate on formats or constraints.

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 returns contract obligation data by vendor, agency, NAICS code, and fiscal year from USASpending, with a specific verb ('Returns') and resource. It also names three distinct use cases (federal revenue concentration, competitor identification, vendor dependency) that distinguish it from generic benchmark tools. The specificity of source and filters makes its role unambiguous among the many sibling data tools.

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 begins with 'Use when researching...' and enumerates three concrete scenarios, providing clear context for when this tool is appropriate. However, it does not explicitly exclude use cases or name alternatives, such as get_vendor_contract_intelligence or get_gpo_contract_benchmark, so the guidance lacks explicit when-not-to-use or alternative routing.

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