token_watch

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

No annotations are provided, so the description carries the full burden and does so well: it enumerates what triggers alerts (grade downgrade, honeypot, sell tax, new flags, price/liquidity moves, holder concentration), the alert_level enum, the baseline/cursor state model, supported chains, cost ($0.008 USDC/call) and p99 latency.

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?

Purpose and delta semantics are front-loaded, and every clause (chains, params, cost, latency) carries operational value. It is a dense run-on paragraph with stacked em-dash lists, so slightly less scannable than ideal.

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 stateful, multi-chain monitoring tool with no output schema, the description supplies the state model (baseline + cursor), alert levels, chain coverage, cost and latency — everything an agent needs to invoke and budget the call correctly.

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 75%, and the description adds meaning beyond it: 'chain (default base, solana auto-detected)' documents auto-detection that the enum alone does not reveal, and it recaps token/price_move_pct/cursor roles consistently with the schema.

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 verb and resource ('re-checks a token on-chain and reports only what changed since your last call') and immediately names its sibling equivalents ('Same checks as token-verdict and token-security'), so the agent can tell this is the delta/on-change variant rather than the full-check tools.

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?

Gives concrete lifecycle guidance ('First call saves a baseline and returns a cursor; pass it on the next call') and positions it against siblings token-verdict/token-security. It stops short of explicit when-not routing (e.g. 'use token_verdict for a one-shot full assessment'), so a 4 rather than 5.

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