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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds real context beyond that: the comparison holds captured inputs constant and drops exactly one expiry, it returns gross shares plus per-strike attribution, and it explicitly disclaims being a post-expiry forecast or dealer-inventory prediction. That interpretive guardrail is genuinely useful for an agent reasoning about the numbers.

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?

Two tightly packed sentences: what is compared first, then output shape and the not-a-forecast caveat. No filler, though the 'Growth+' prefix carries little meaning for an agent.

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?

With no output schema, the description does the work of naming the return content (gross shares, per-strike attribution), and annotations cover the read-only profile. What is missing is the relationship to sibling gamma tools and any note on latency or data recency for the 'captured inputs' baseline.

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%, with limit, apiKey, expiry and symbol all documented in the schema itself. The description only echoes the symbol scope (SPY/QQQ) and the one-expiry exclusion already implied by the expiry parameter, adding no syntax or format detail. Baseline 3 is correct.

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?

States a specific verb (compare) and a specific resource (current SPY/QQQ gamma concentration with one expiry excluded), including the counterfactual framing that makes this distinct from a plain GEX read. It never names a sibling tool such as get_gex or get_exposure_sheet, so differentiation is left to inference.

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 closing clause ('a sensitivity calculation, not a forecast of post-expiry price or dealer inventory') scopes the tool's interpretation but does not say when to reach for it over the many gamma/exposure siblings. Usage is implied rather than stated, with no alternatives or preconditions named.

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