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

With no annotations, the description carries the full burden and delivers exceptional disclosure: missing/stale data behavior ('missing/stale is said on the row, name stays, no number invented'), explicit null semantics in sleeve rows, ranking definition ('ordering + attached DATA'), safety rails ('FIRM never places', 'do_not_place_from_mover_rank stays true'), cache/TTL behavior ('the 300s TTL does not evict the last ranked sleeve'), latency, and Auth: X-API-Key. It precisely bounds what the tool will and will not do.

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 description is dense with no filler — every clause carries meaning, and the SCAN/RANK/SLEEVE core is front-loaded. The run-on single-paragraph format with capitalized bursts and config-style fragments ('edge=no_measurable_edge', 'do_not_place_from_mover_rank stays true') slightly hurts scannability and reads like literal assignments rather than prose.

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 tool with no output schema and no annotations, the description covers the operational contract thoroughly: universe semantics, data bundles, row contents, safety, performance, and auth. It falls short of complete by not defining the exact response shape, how min_price/min_adv_dollars are applied, or empty/failed-filter behavior.

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 0%, so the description must compensate; it explicitly explains sleeve_n ('bounded top-N (default 20)' matching the schema default). However, min_price and min_adv_dollars are left to name inference with no statement of how they interact with the pipeline — whether they filter the universe before ranking, exclude rows, or annotate them. The SCAN/RANK/SLEEVE context helps, but the two min_* filters lack explicit semantics.

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 specific verbs and a resource: SCAN the full tradeable US equity book, RANK it with attached DATA, and SLEEVE a bounded top-N. It distinguishes itself from siblings by scope — 'US equity' vs tengu_crypto_sitting, 'measured count, never a hardcoded 8000 or a 20-name seed list' vs fixed-universe tools, and 'not a Tengu score' vs scoring/ranking tools.

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?

'ONE sitting contract for the autonomous desk' clearly marks this as the canonical equity-sleeving entry point, and the equity/crypto split routes the agent among siblings. Exclusionary statements ('not a Tengu score', 'do_not_place_from_mover_rank stays true', 'FIRM never places') tell the agent what this tool is not for, but no sibling is explicitly named as an alternative, keeping it below a full 5.

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