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

Annotations already declare read-only, idempotent, non-destructive. Description adds the derivation methodology (z-score vs 252-day history) and access tier restrictions for specific blocks, which is useful context beyond annotations.

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?

One dense sentence that packs all key components plus a second sentence for tier limits. Efficient, but the first sentence is a long list; still, each element adds specificity.

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?

Covers what the digest contains, the unusualness score formula, and access constraints. Output schema exists, so return format is handled elsewhere. Missing discussion of interpretation or edge cases, but sufficient for selection.

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 only has 'ticker' as a required string with no description. The description clarifies that the parameter is the ticker symbol ('per-ticker', 'today's factor state vs the ticker's own history'), adding meaning despite zero schema coverage.

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 clearly identifies this as a per-ticker digest with specific components (factor snapshot, percentile ranks, risk-cluster, market regime, unusualness score). It distinguishes from sibling tools like get_market_regime or get_risk_cluster by presenting this as a combined derived digest.

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?

Provides concrete tier requirements (HOBBY tier or higher; risk-cluster block requires PRO) but doesn't compare explicitly to sibling tools or state when to prefer this over them. Context implies usage for a quick per-ticker summary.

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