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

Annotations already declare the safe read-only/idempotent profile, yet the description adds substantial behavioral detail not in the structured data: live fields refreshed 'from the mint feed every 5 s', the staleness rule (refuse rows without mints_since_asof), the null-never-false semantics of known_bad, the distinction between recount-dated and live fields, and the *_proven false flags. That is exactly the kind of context annotations cannot carry.

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?

A single monolithic run-on paragraph that mixes purpose, output-field documentation, freshness semantics, census-rule caveats and warnings with no headings or ordering. The purpose is front-loaded in the first sentence, but everything after is an undifferentiated stream that an agent must parse word by word; many clauses exist to document return fields that have no output schema to live in.

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 full burden of explaining the return shape and largely does so: known_bad, rug rate, chain baseline, multiple, ttr_median/p25/mean with ttr_n and n_rugged, rugged_resolved/faded_resolved as x/y, plus the live fields. It is nearly complete, though the dense packing makes it easy to misread which fields are live versus historical.

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 100%: chain's enum/default and creator's address formats (base58 / 0x...) are already documented in the schema. The description's parameter-like sentences — the 'kol' block — describe output fields rather than either input, so it adds nothing for creator or chain. Baseline 3 applies.

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 does state what the tool returns in decision form: 'is this creator known bad, with the rug rate, the chain baseline and the multiple that justifies the verdict', and it differentiates from the wallet-list sibling ('use it when all you need is the decision rather than the wallet list'). However, this is buried under a wall of field-level jargon (TTR, asof, proven flags), and it does not distinguish itself from other creator-scoped siblings like screen_creator, creator_replay or scorecard. Clear purpose, weak sibling differentiation.

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?

There is explicit usage context — 'The cheapest call on this server -- use it when all you need is the decision rather than the wallet list' — which routes the agent away from the wallet-list tool. It also adds an operational rule ('A row with no mints_since_asof is not live: refuse it') and a warning that peak/pull/ttr are 'not a trade signal'. No other named alternatives or exclusion conditions are given.

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