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

The description fully carries the burden due to no annotations. It explicitly states the data recency (last 180 days), types of events returned (win/lose/modify), and that events accrue over time. This is good transparency, though it omits potential limitations like pagination or number of results.

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 a single, well-structured sentence that conveys all necessary information without extraneous words. It is front-loaded and efficient.

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 one parameter and no output schema, the description covers the main functionality and data scope (180 days, events). It does not describe the return structure, but the context is sufficient for an agent to understand the tool's purpose and when to use it.

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 single parameter 'contractor' is described as 'contractor name' in the description, adding context beyond the bare string type in the schema. However, it does not specify expected format (e.g., exact name, partial match), which could leave ambiguity.

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 takes a contractor name and returns recent federal awards and win/lose/modify events. It specifies the time window (last 180 days) and event types, distinguishing it from sibling tools like search_awards (general search) and delta_digest (diffs).

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 implicitly suggests use for monitoring a specific contractor's activity, but it lacks explicit guidance on when to use this tool versus alternatives (e.g., search_awards for broader queries). No when-not-to-use or exclusion criteria are provided.

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