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

Annotations only declare readOnlyHint=true, so the description carries the burden of behavioral disclosure. It reveals that the tool performs OLS regression, includes maxStepDelta to detect spike-reversals, relies on injected history, uses the sumOpenInterest field, and outputs raw numbers with no categorical labels. This is substantial behavior beyond the structured annotations.

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 a single dense sentence that front-loads the core computation, then adds the extra metric, rationale, sibling reference, injection rule, and output format. It contains no filler, though the heavy use of uppercase markers adds visual noise.

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 computation tool with no output schema, the description covers the input source, algorithm details, the specific field to use, and the nature of the output ('angka mentah saja'). It does not enumerate the exact return fields, but both the slope and maxStepDelta outputs are referenced, making it sufficiently complete.

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 descriptions cover symbol and velocityWindowIntervals but say nothing about oiHistory. The description fills that gap by specifying that oiHistory must come from binance_get_open_interest_history and that sumOpenInterest is the relevant field. It also reaffirms the interpretation of velocityWindowIntervals by matching compute_funding_velocity's default.

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 precise operation: compute open interest velocity per hour via OLS regression over the last window, plus the largest consecutive-point jump (maxStepDelta). It explicitly distinguishes this from compute_funding_velocity by saying it uses the same method but for OI, and clarifies that it does not fetch history itself, separating it from data-fetching siblings like binance_get_open_interest_history.

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 gives explicit instruction to pass the result of binance_get_open_interest_history rather than fetching data, which is a clear when/what-not-to-do. It also cross-references compute_funding_velocity as the analogous tool for funding velocity. It does not, however, provide an exhaustive when-to-use comparison against all siblings.

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