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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely non-obvious behavior: signals carry an access label, opportunities on a free plan or without sign-in are delayed 24 hours, and outcomes are only populated 'once scored'. That freshness/plan gating is valuable and not derivable from 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?

Purpose is front-loaded in the first clause and every sentence carries information (signal taxonomy, access gating, pagination). The heavy nested parentheticals make it denser to parse than ideal, but there is no filler.

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 return-shape burden and does so: 'the exact ticks,' the realised outcome once scored, and the per-signal access field. Pagination is covered via `before`. Auth requirements for the `source` values remain slightly under-explained, but the picture is largely complete.

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%, so the schema already documents limit, before, and source. The description earns credit by explaining the meaning of the `kinds` enum values themselves (net_apr = high net APR range over 7 days and still today; burst = last hour; hot_pool = fee APR jump), which the schema does not. It omits any explanation of `smart_lp`, and doesn't add to `source`/`limit`.

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 ('the newest signals') and enumerates what those signals are (net_apr, burst, hot_pool, depeg, tvl_outflow), giving the agent a precise picture of the payload. It never names sibling tools like signal_track_record, so the boundary is inferred rather than stated.

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 operational guidance for pagination ('Page back with before') and explains access tiers (live vs delayed_24h for free/no-sign-in), which is helpful context. However, it never says when to prefer this tool over signal_track_record or smart_lp_leaderboard, so usage against alternatives is only implied.

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