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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral detail: it explains that channel selection 'nulls non-selected fields' and that CME data is often null with the status 'cme_source_not_procured'. It also reiterates the read-only/public nature and adds that it is not investment advice. These behaviors go beyond the annotations and inform the agent about data quality and side-effect‑free invocation.

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 roughly 70 words and front-loaded: it states the core purpose first, then parameter guidance, then key data-quality notes, then safety/scope. There is no fluff; every sentence introduces a distinct fact (purpose, parameter semantics, null behavior, return shape, read-only nature). The structure is efficient and scannable.

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 the 5 optional parameters, full schema coverage, an output schema (present per context), and annotations covering safety, the description covers everything an agent needs: it explains parameter semantics, return structure, and data-quality quirks (CME nulls). It even clarifies that this is public research data and not investment advice, preventing misuse. Nothing critical is missing.

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 schema already documents all five parameters and their defaults (coverage 100%), so the baseline is 3. The description provides additional nuance: it clarifies the enum-style values for asset and channel, and explains that selecting a channel nulls non-selected fields—something not explicitly in the schema. It also notes the relationship between CME nulls and the data_status field. This adds real meaning beyond the schema descriptions.

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 states a specific purpose: 'BTC/ETH institutional ETF/CME/CFTC daily metrics' and goes on to clarify the data source (OpenSearch) and the structure of results (assets[].latest and series[]). This clearly distinguishes it from sibling market snapshot and overview tools, which focus on general market data, not institutional metrics. No ambiguity remains about what it does.

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 does not explicitly name alternatives or state when not to use this tool, but it provides clear context: it is for institutional ETF/CME/CFTC metrics, read-only research data, and is explicitly not for trading or account actions. Given the narrow scope, an agent can infer when to call it, and the 'Read-only' note signals it is safe for research. However, it does not mention any sibling that covers overlapping data, so the exclusion guidance is implicit rather than explicit.

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