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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description goes well beyond them: default truncation of back-history to the newest 3 points per series with a `history` block reporting how many were omitted, `history=true` roughly doubling answer size, null-not-zero semantics for pending ETF days, null for unshown venues, `newest_partial`/`newest_bar_open` meaning, and that clock verdicts are judged at answer time. That is unusually rich behavioral context for a read 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?

It is one dense wall of prose with heavily nested parentheticals and no headings or bullets, which makes a genuinely intricate payload harder to parse than necessary. Some of the field-level vocabulary is justified given no output schema, but the most decision-relevant facts (default history truncation, sibling routing) are buried at the end rather than front-loaded, and other sentences could be tightened without loss.

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, one optional parameter, and a very wide payload, the description accepts the burden of defining each field's semantics, null behavior, cadence and timing. It is close to complete for correct interpretation, though it says nothing about error/failure behavior or what 'beta' implies for stability.

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% on the single `history` boolean, so the baseline is 3. The description still adds meaning the schema lacks: the default back-history is the newest 3 points per series, the full stored series is returned when true, and the response carries a `history` block reporting omitted points. That is real value beyond the property's own description.

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 first two sentences name a concrete resource domain — the BTC derivatives market — and enumerate exactly which metrics are covered (funding, OI, liquidations, long/short, taker volume, ETF flows, max pain, fear/greed), and it explicitly points sentiment to mcw-signals-sentiment and feed verdicts to mcw-signals-meta. The only weakness is that there is no crisp declarative verb — the purpose is conveyed as a field catalogue rather than 'returns X', and the statement of what is actually returned (latest reading of every metric, 3 back-history points) is deferred to the very end.

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?

It explicitly routes the agent to alternatives for adjacent data ('TSP's sentiment readings are in mcw-signals-sentiment, and its verdict on each price feed in mcw-signals-meta') and tells when to flip `history` ('Set `history` to true for the full stored series'). It gives clear context but no exclusion conditions and does not distinguish itself from mcw-signals-charts or mcw-signals-overview, which likely overlap.

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