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

With no annotations present, the description carries the full disclosure burden and delivers thoroughly: it discloses which fields are not versioned (contract permissions, supply events, development activity), that an empty change list never implies stability, that resolution is none when history is too short, and how baseline drift surfaces in window.baseline_drift_days. This is exactly the edge-case behavior an agent needs and far exceeds typical coverage.

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?

A single dense paragraph, but every sentence carries load-bearing information: purpose is front-loaded, and each caveat (not_versioned, resolution none, baseline drift, ratings disclaimer) addresses a distinct failure mode. It could be easier to scan with bullets or headers, but there is no redundancy or 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?

Despite having no output schema and no annotations, the description covers the return shape in detail (before/after pairs, deduction state changes, signals opened/resolved, not_versioned, resolution:none, baseline_drift_days) plus the edge cases that would cause misinterpretation. The only missing element is explicit sibling routing, which is minor given how purpose-specific the text is.

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 100% with both parameters already described, so the baseline is 3. The description adds genuine parameter behavior beyond the schema — the since parameter's nearest-earlier-observation baseline and the meaning of window.baseline_drift_days — which helps an agent interpret the window it actually requested.

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?

Opens with a specific verb-plus-resource — 'what changed for an asset since a moment' — and enumerates the exact output fields (rank, price, market cap, volume, turnover, survival score/band, deductions, signals) framed as before/after comparisons. The temporal-diff scope is immediately distinguishable from sibling names like coingraph_get_asset or coingraph_compare, even though it never names them.

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?

No alternative tool is named and no explicit when-to-use vs when-not-to-use guidance is given; usage is implied by the purpose statement. The description does provide clear interpretive context for results (check window.baseline_drift_days, treat resolution:none as missing history), but stops short of routing the agent toward siblings like coingraph_compare.

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