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

The description adds meaningful behavioral context beyond the annotations: stateful behavior ('since your last check', 'pass back next_since_ms on a timer'), result clamping ('more is clamped and said' in the limit param), unusualness ranking, and the brief/full detail split. Annotations already cover the read-only, idempotent safety profile, so no contradiction exists; the description enriches the operational picture.

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 opener 'The whole market in one call' front-loads the purpose well and every clause adds information rather than padding. But the body is a single run-on sentence with nested parentheticals and semicolons exceeding 80 words, making it notably hard to parse; per-view bullets or line breaks would drastically improve scannability.

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 5-view, 7-parameter tool with an output schema and safety annotations, the description covers all views, the stateful since-last-check behavior, pagination via cursor/next_since_ms, and the brief/full detail split. Minor gaps like explicit auth/rate-limit mentions and error behavior are not critical for a read-only aggregator.

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%, so the baseline is 3. The description carries real semantic weight for the central view parameter — the schema explicitly defers ('Which lane; see the description') and the description defines each lane's payload. It also adds the since_ms/next_since_ms timer protocol and cross-parameter behavior ('overview ... pass coin for one row') that the schema does not.

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 opener 'The whole market in one call' names the verb-resource pair and positions this as the market-wide aggregator tool, and each of the five view descriptions states exactly what that lane returns. This clearly distinguishes it from siblings like coin_brief (single coin), market_screener (screening), and news (news feed).

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?

The per-view breakdown gives clear implied context for when each lane is appropriate (changes for what moved since last check, movers for 24h gainers/losers, defi for DEX volume/TVL). However, no sibling alternatives are named and there are no explicit when-not-to-use or exclusion statements, so deciding between market_now, market_screener, and coin_brief is left to inference.

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