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

Annotations already cover the read-only, idempotent, non-destructive profile, and the description adds genuinely new behavior: the price source is book mids where stored and falls back to marks otherwise, plus explicit plan-based limits on granularity and history depth. It stops short of anything about response shape or failure modes when an instrument lacks stored mids.

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?

Two dense sentences, front-loaded with the definition and followed by the constraint that most affects tool choice. Every clause carries information; nothing is redundant with the title or schema.

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 read-only two-leg series tool with no output schema, the description covers what is computed, from what data, and under what tier limits. The one material gap is the undocumented `executable` flag, which changes what the spread actually measures.

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?

With only 40% schema description coverage, the description must carry weight: it does effectively document the `candle` and `days` constraints (granularity tiers, max history) and the (A − B) / B formula implies the roles of leg_a and leg_b. However, `executable` (default false) is never mentioned anywhere and its effect on the computed spread is completely opaque.

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 specific output (candles) and a precise mathematical definition ((A − B) / B) over two instruments, which uniquely identifies the operation. It does not name or contrast with any sibling such as pair_history or basis_trades, so an agent must infer whether a spread chart or a basis series is wanted.

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 description gives tier-based constraints (Free: 1h+, ≤7 days; Pro: 1m+, ≤365 days), which is useful gating information, but it never says when to reach for this tool rather than a sibling or what prerequisites (valid instrument ids, entitlement) apply beyond the tier note.

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