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

Annotations cover the safety profile, and the description adds things they cannot: a 15s cache, partial-failure semantics (a failed section is null with its reason in `errors` while the rest stay valid), and per-section `computed_at`/`data_as_of` freshness. It also encodes the non-obvious grading semantics — grey is not a red flag and should not cause a skip, while red causes Moby to refuse agent buys — which is exactly the behavioral context an agent needs to act correctly.

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?

Front-loaded with the routing instruction and the value proposition before the detail, and nearly every clause carries actionable semantics (win_rate >= 0.5 threshold, top-10 >= $100, `pct_from_ath` basis). The long enumeration of report sections overlaps with the existing output schema, which is the main slack, but the enumerated tiers and thresholds still earn most of their space.

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?

Given a rich output schema, a caching layer, degradation behavior, and a `data_notes` mechanism, the description covers everything an agent needs: what a null means, what `data_notes` implies about verification, how to treat each `safety_tier`, and the falsification duty ('check the web before quoting'). No material gap remains for correct invocation and interpretation.

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 0%, so the description carries the full burden, but it never discusses the two parameters. It implies a single token ('on one token') yet gives no address format, no statement of whether tickers are accepted (search_tokens is the sibling for that), and never mentions the `network` parameter at all.

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 — a one-call pre-trade research brief on a single token — and quantifies the payoff ('a few KB in one call instead of 5-10'). It explicitly positions itself as the entry point and names the siblings it replaces, so an agent can distinguish it from get_token_overview or get_token_live_feed 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?

Opens with 'START HERE' and then routes the agent in both directions: which sibling to use to go deeper and why (paging, every trade, rate holders, re-polling a pending scan, price action, full read). It also draws a clear scope boundary, telling the agent this is market data, not user data, and that `get_my_*` tools are the ones for the user's own wallet.

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