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

Beyond the readOnly/openWorld annotations, the description adds important behavioral details: it reveals per-program result structure, distinguishes cash itineraries paired with award pricing from award-only itineraries, and defines the timeout vs no_results response states. It clarifies what the open-world nature means in practice for polling.

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 compact yet complete, with a clear opening purpose, explicit call sequencing, return summary, and edge-case semantics. Every sentence contributes unique, operationally useful information without redundancy.

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 read-only polling tool with an output schema, the description covers the necessary context: prerequisites, parameter intent, expected response contents, and how to interpret ambiguous statuses. Nothing critical is missing for an agent to invoke it 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 coverage is 100%, so the baseline is 3. The description adds value by explaining the consequence of omitting pending_sources (polling every program, including those never searched), which goes beyond the schema's parameter description. Other parameters are adequately covered by the schema and the description's context.

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 uses a specific verb ('Collect award pricing') and resource ('a flight search'), and clearly distinguishes this from other sibling tools by tying it to search_flights responses with pending_sources. It avoids the tautology of the tool name and explains the exact domain.

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?

It explicitly states when to call this tool: after search_flights with points:true and a pending_sources response. It also explains why pending_sources matters, but it does not explicitly mention alternatives or when-not-to-use scenarios, leaving room for a higher score.

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