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

With no annotations provided, the description carries full behavioral disclosure. It covers output granularity (one row per trading day vs. full strike ladder), required input constraints (date OR start+end), error condition (422 for >30 days), data coverage start, and cache duration (10-min). This is comprehensive for a read-only historical data tool.

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?

Five sentences, each with a distinct purpose: what it is, when to call it, what it returns by default vs. per_strike, required parameters and limits, and cache behavior. Front-loaded with the core purpose, efficient and information-dense with no 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 no output schema, the description explains returned fields well for both modes. It includes constraints, error condition, and coverage start. Missing details like the 'limit' parameter, date format (e.g., YYYY-MM-DD), and whether date conflicts with start/end leave minor gaps, but overall it is highly usable for an agent to invoke the 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 coverage is only 17%, so the description must compensate. It explains date, start, end (as an OR requirement), per_strike (default vs. true behavior), and implicitly ticker. However, it omits the 'limit' parameter entirely (default 10000, max 50000), leaving its purpose unclear. The described constraints and options add significant meaning beyond the bare schema, but the gap on limit prevents a 5.

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 opens with 'Historical dealer gamma-exposure (GEX) for one ticker', clearly stating the resource and temporal scope. It explicitly distinguishes itself from the live /intel/gex tool and provides a concrete use case ('how did dealer positioning shift into OPEX / earnings?'), which removes ambiguity for agent selection.

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 names the live counterpart tool ('behind the live /intel/gex tool'), letting agents choose history vs. live. It also gives a specific invocation scenario ('Call for ...') and explains the default vs. per_strike=true modes, which is practical guidance for when to use each option.

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