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: it discloses that every value carries its own observed time, what `freshness` means, that inputs are judged per series cadence (judged_on[].cadence_check, per-family staleness, ETF flows by two days), and the honest limitation that TSP does not state the delta_pct period. It also flags 'beta' status and that no trade levels are published.

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 front-loaded with the scope ('Bitcoin only, beta') but then unspools into a single very long run-on sentence dense with nested parentheticals, making it hard to parse. Nearly every clause carries information, but the structure does not help an agent scan it quickly.

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 and no parameters, the description must carry the full burden of explaining what comes back, and it largely does: enumerated content, freshness/staleness semantics, label ownership, and caveats. It is slightly short of complete because the exact shape and keys of the returned structure are only partially enumerated.

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 tool takes zero parameters, so the baseline is 4. The description nonetheless explains return-field semantics such as `spot.delta_pct` being in percent, `most_probable_arm`/`dominant_case`, and `judged_on[].cadence_check`, which adds meaning even though no input parameters exist to clarify.

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 resource and enumerates its content precisely: BTC spot price with delta_pct, trend/direction/confidence across thirteen timeframes with consensus, bull/base/bear cases with probabilities for three horizons, and recurring support/resistance. It also fixes scope ('Bitcoin only') and explicitly defers thesis labels to mcw-signals-thesis, so an agent can place it against siblings such as mcw-signals-market-data and mcw-signals-charts.

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?

There is no statement of when to choose this tool over mcw-signals-charts, mcw-signals-market-data, mcw-signals-sentiment or mcw-signals-thesis. The only routing hint is that thesis labels are defined in mcw-signals-thesis, which is a definition pointer rather than usage guidance, and the content exclusions ('no entry, target or stop is published') describe data scope, not when to call this.

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