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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: the unauthenticated tier is capped to "the first 10 coins at the daily close," which materially changes what an agent should expect. It omits return shape and row limits for authenticated calls, keeping it below a 5.

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?

Information is front-loaded: purpose first, then condition grammar, then the free-tier caveat. The measure enumeration ("v the reading, p1 p7 p30 p90 p365...") is dense and slightly run-on, but nearly every clause carries operational meaning, so there is little waste to cut.

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 6-parameter, all-optional tool with no output schema, the definition covers the hard parts: filter grammar, sorting columns, interval resolution pointer, and the keyless limitation. What is still missing is what a response row looks like and any row-count ceiling on authenticated calls, which an agent would need to plan around.

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%, so baseline would be 3, but the description goes far beyond the schema by defining the condition grammar itself: `field:measure op number`, the all(...)/any(...) combinator logic, and the full measure alphabet (v, p1–p365, d1–d365, z, q). This tells an agent how to construct valid `where`, `sort` and `columns` values in a way the raw schema never does.

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 opens with a specific verb and resource: "Screen every coin CryptoKeyhole covers by the latest readings of its charts," and immediately grounds it in concrete example conditions (MVRV below 1, funding below zero, price 60% under its high). An agent can distinguish this screening/filtering tool from siblings like fetch_metric or find_extremes without opening any 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 clear context for when to use it (filtering the whole coin universe by chart conditions) and points to get_screener_fields for valid field ids, plus a stated fallback for keyless callers. It stops short of explicit exclusions, e.g. when to prefer find_extremes or fetch_metric over a screen, so the alternative-selection guidance is only partial.

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