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

Annotations already declare read-only, idempotent, non-destructive, and closed-world, but the description adds real context beyond them: data is collected every 6 hours and audited before publishing, null means unknown, every number carries {value, unit} and as_of, and it explicitly frames itself as 'a research screen, not a signal.' These freshness, null-semantics, and disclaimer disclosures are genuinely useful and not derivable from the annotations.

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 description is a ~250-word run-on dominated by parenthetical field enumerations, with the actual task statement buried in the first clause and no paragraphing or bullet structure. Almost none of it is front-loaded and much of the field listing repeats information the payload itself would carry.

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, the description carries the burden of explaining returns, and it does enumerate the payoff fields, their shapes, and sources/freshness extensively. For an agent deciding whether to call it, nothing essential is missing, though the sheer volume makes it hard to extract the key facts.

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% and documents the single symbol parameter, so baseline is 3, but the description adds meaning the schema does not: case-insensitivity and the tie-break rule that a shared ticker resolves to the largest market cap. That said, most of the description is about the return payload rather than the input.

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 concrete verb+resource ('One coin in full by slug ... or ticker') and implicitly scopes it as the per-coin detail view distinct from sibling list tools like gem_screener_ranked and gem_screener_picks. An agent can tell what it returns, though the framing question ('is this token a gem or a casino?') and the avalanche of field names obscure the core statement. It is clear but not cleanly differentiated from every sibling.

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 explains lookup mechanics (slug or ticker, case-insensitive, shared ticker goes to largest market cap) and alludes to the picks gate, but never states when to reach for this tool versus gem_screener_ranked or gem_screener_picks. Usage is implied rather than directed.

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