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

Annotations already declare read-only/idempotent/non-destructive. The description adds substantial context: it never returns raw external odds, requires no auth, includes a citation expectation, is not investment advice, and explains the computation basis from market contracts and news stories. This exceeds annotation coverage.

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 front-loaded with a clear definition and each sentence contributes substantive detail about the metric, returns, restrictions, and caveats. Slightly dense but no wasted words; appropriate length for the complexity.

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 lists the returned fields per item (divergence value, news-narrative probability, market descriptor, story links, venue link), covers filtering, auth, and disclaimers. This is sufficient for an agent to correctly invoke and interpret results, though it omits edge cases like empty results.

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?

Input schema has 100% coverage for both parameters (limit with min/max/default, source with allowed values). The description only restates 'Filter by source' without adding new semantics. Baseline 3 is appropriate.

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 states it returns Storyflo's computed divergence index, explaining the metric (gap between market-implied and news-narrative probabilities), ranking by absolute divergence, and listing returned attributes. It distinguishes the tool as 'ORIGINAL ANALYSIS... not market-data redistribution,' setting it apart from sibling 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?

The description gives clear context on what the tool offers (original analysis, not raw odds) and notes it's public/no auth. It excludes raw market odds but does not explicitly name alternative tools for that need, so it falls short of explicit when-to-use/alternatives.

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