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

Goes well beyond the annotations: discloses the return contents (sample dates, weeks, pair observations, confidence intervals, price-only exceptions, exclusions, covered value share), states a no-inference guarantee ('never infers a numeric correlation from allocations or holdings'), documents the unavailable failure mode, and specifies required consent/entitlement. This is rich behavioral context for a read-only 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?

Front-loaded with the core purpose and use case, then supporting behavioral detail. Dense but each sentence carries information (returns, guarantees, failure mode, auth). Slightly long, but none of it is wasted 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?

For a 4-param read tool with an output schema, this is complete: it covers what is returned, the no-inference guarantee, auth/entitlement requirements, the unavailable path, and pagination continuation. An agent has everything needed to call it correctly and interpret edge cases.

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 0%, so the description must compensate. It adds meaning to `window` ('requested historical window') and `computed_at` ('Send computed_at on further pages'), effectively documenting the pagination cursor. However, `limit` and `offset` are never explained beyond the vague 'further pages' hint, leaving half the parameters undocumented.

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 and resource: 'Read measured historical weekly EUR return correlations' from the canonical correlation-lens observation. It separates itself from the closest sibling by noting it is 'for how held investments moved together... not constituent overlap', so an agent can distinguish it from holdings/analysis tools without opening schemas.

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?

Explicitly frames the use case ('how held investments moved together over the requested historical window') and an exclusion ('not constituent overlap'). It also states entitlements/consent needed to invoke. It stops short of naming a sibling alternative tool by name, but the when/when-not framing is clear.

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