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

The annotations already cover read-only, idempotent, non-destructive behavior, so the description goes further by documenting null semantics ('a tile is null when its inputs were not read'), the schedule_published flag, and the rule that dilution_12m_pct and yearly_pct are null — never 0 — when no schedule is published. That's a real behavioral contract beyond what annotations provide. It doesn't state rate limits or caching behavior, but that's a minor omission.

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 single overloaded run-on sentence that crams tile definitions, invocation paths, null semantics, record fields, and disclaimers together without paragraph breaks or ordering. It is dense and hard to scan, and front-loading is poor — the key invocation choice (symbol vs. contract+chain) appears after a long parenthetical about tiles.

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 read-only analyzer with no output schema, the description does substantial work: it names every output field (tiles, next unlock, out_by_month, inputs[], unknown_names[], months[], refreshed_at), explains null and schedule_published semantics, and clarifies that a null tile means inputs weren't read rather than zero. An agent can form a correct mental model of the response. It stops short of explaining the tile structure in enough detail to parse it programmatically, which is the main gap.

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 description coverage is 100%, so the schema already documents chain, symbol, contract, and include_months. The description adds semantic nuance the schema lacks: that a ticker shared by two tokens returns AMBIGUOUS_TICKER with the options, and that symbol can be a ticker, slug, or CoinGecko id. That's useful but incremental over the schema's own descriptions.

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 states a specific resource (token supply) and enumerates the exact outputs: five tiles, next unlock, out_by_month, plus the record fields (inputs[], unknown_names[], months[], refreshed_at). This is far more specific than the name alone. It doesn't explicitly contrast with the sibling supply_analyzer_batch, but no other sibling covers token supply, so the risk of confusion is low.

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 two concrete invocation paths: pass symbol for a Gem Screener coin, OR contract + chain for any token, and names the data sources for each (DeFiLlama price, chain totalSupply). What's missing is guidance on which path to prefer when both are available, or what happens on failure paths beyond AMBIGUOUS_TICKER.

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