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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-structured behavior: the tool is 'Bitcoin only, beta,' the snapshot can be 'degraded' with a reason, sources may be 'carried from an earlier run,' and each source carries its own observed time — all of which shape how an agent should interpret the result. It stops short of stating return format or how staleness thresholds are computed.

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 purpose and the Bitcoin/beta constraint are front-loaded, and the later sentences, while dense with field names and backtick references, each carry distinct information about the response. It reads as one long paragraph with a somewhat sprawling final sentence on the TSP-vs-Wire verdicts, so structure could be tighter, but there is little true 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?

With no output schema and no parameters, the description carries the full burden of explaining what comes back, and it does so thoroughly: timing, age, degradation, per-source provenance, the two competing freshness verdicts, and the beta/not-advice notice. An agent has enough to decide whether to call it and how to read the result.

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 per the rubric the baseline is 4. The description instead spends its budget on the shape of the returned fields (feed_freshness, tsp_status, verdict_at, wire_check, verdicts_differ), which is the right allocation here.

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 names the specific resource (the BTC signals snapshot) and enumerates exactly what it reports: snapshot time, age of newest value, degradation state and reason, per-source observed times, carried-forward flags, and the beta/not-advice notice. It explicitly distinguishes itself from siblings — 'the only one of the signals tools that is purely about the age of the data' — so an agent can separate it from mcw-signals-overview, -market-data, -thesis, etc. without opening a schema.

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 gives a clear selector condition: this is the signals tool to reach for when the question is data freshness rather than content, and it clarifies that tsp_status and wire_check are two independent verdicts where 'neither replaces the other.' That is useful routing context, but there is no explicit when-not or a named alternative for related questions (e.g. where to go for values rather than age).

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