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

Beyond the readOnlyHint/idempotentHint annotations, the description details fallback behavior (GDELT→GNews on rate-limit/5xx), soft-fail due to USPTO API sunset, and the parallel fan-out execution model. These are behavioral facts an agent needs to set expectations, and they add significant transparency.

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 longer than average but front-loads the core purpose and then systematically covers sources, fallback, return shape, and alternative tool. Each sentence carries substantive information, so the density is justified; however, a bit of pruning could improve scannability.

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 compensates by explicitly stating return structure (changes[] grouped by source, total_changes, citation URIs), enumerating all sources, and disclosing failure modes. This gives an agent everything needed to invoke the tool and interpret results, making it fully complete.

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?

While schema coverage is 100%, the description enriches the 'since' parameter by tying it to the window applied across sources (filings since `since`, news in window) and offers practical guidance ('Use "30d" or "1m" for typical monitoring'). This adds contextual semantics beyond the raw format descriptions.

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 opens with natural-language query examples and a precise definition: 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It explicitly names the data sources (SEC EDGAR, GDELT→GNews, USPTO) and contrasts with sibling tool entity_profile, fully distinguishing it from alternatives.

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?

It provides explicit when-to-use triggers ("What's new with X", "latest on Y") and an explicit exclusion: 'Use entity_profile instead when you want the static profile...'. This gives clear contextual guidance with a named alternative, going beyond mere implication.

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