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

Annotations only declare readOnlyHint/destructiveHint, and the description adds real operational context beyond that: the call costs exactly ONE quota request, returned values are at most 60 s old, and pairs lacking the metric appear in an `excluded` bucket rather than silently vanishing. These are exactly the traits an agent needs to reason about cost and result completeness for a read tool.

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 definition is front-loaded with the core contract (rank by one metric, top limit, one quota request) before metric definitions and the example, with no filler sentences. The telegraphic, comma-spliced style is dense and slightly hurts scannability, which keeps it from a 5.

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 an 8-parameter, no-output-schema read tool, the description covers cost, freshness, metric semantics, and the `excluded` bucket, while dry_run and max_quota_cost are fully documented in the schema. The remaining gap is that it never indicates the shape of each ranked row (fields per pair), though the lack of an output schema makes that a minor omission.

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% (baseline 3), but the description goes well beyond the schema's bare enum by defining each metric: volume_usd_24h is spot+futures over 24 closed hours in USD, funding_next returns estimated_rate_pct as an 8h rate plus apr_pct, price_change_pct uses `window`, and rsi is RSI 14 on the last closed candle of `timeframe`. That is substantive semantic meaning the schema does not provide.

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 opening clause states a specific verb and scope: 'Every pair ranked by ONE metric, top `limit`', which is a cross-sectional screening operation clearly distinct from per-pair siblings like get_pair_data or get_pair_brief. It also enumerates the five rankable metrics, so the resource is unambiguous. It stops short of naming a sibling to avoid, keeping it at 4 rather than 5.

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?

Usage is implied rather than stated: the 'ONE metric' emphasis signals you can't combine metrics, and the funding example ('most negative funding: metric=funding_next, order=asc') demonstrates a concrete call pattern. However, there is no explicit when-to-use vs. when-to-use-an-alternative guidance, e.g. nothing telling the agent to prefer get_pair_data when it needs multiple metrics or a single pair.

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