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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: it discloses data provenance boundaries ('on-chain order-book fills start 2022-11-21') and by implication that counts are live rather than cached snapshots. It stops short of describing response shape, which matters since no output schema exists.

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?

Everything is packed into one long sentence with nested parentheses, a colon chain, and stray quotes ('the live source for "N wallets / N metrics" figures'), which makes it harder to parse than necessary. It is front-loaded with the core purpose and contains no filler, but the structure could be split into the return inventory plus a provenance note.

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 zero parameters and no output schema, the description carries the return-value burden and largely discharges it by enumerating the fields, with data-start caveat included. Minor gap: 'markets covered' and the metric count are not given field names the way `wallets`, `trades`, and `since_year` are, so the response mapping is only partial.

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?

The tool takes zero parameters, so the baseline of 4 applies; there is no parameter syntax an agent needs to learn. The description instead spends its space documenting the returned fields, which is the appropriate substitute for a parameterless call.

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 concrete resource (platform coverage stats) and enumerates the specific quantities returned: wallets scored, raw fill events (`trades`), markets covered, metric count, and `since_year`. The phrase 'the canonical ... count' implicitly contrasts with `polyrank_get_metrics_catalog`, which lists metrics rather than counting them, but the sibling is never named, so differentiation is left to inference.

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 only implied by 'the live source for "N wallets / N metrics" figures' — an agent can infer this is for headline/quote figures rather than per-trader analysis. There is no explicit when-to-use statement, no when-not-to-use, and no named alternative (e.g. use the metrics catalog for the metric list itself).

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