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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description goes far beyond annotations, disclosing non-obvious behaviors: it 'fans out' in parallel, uses a GDELT→GNews fallback on rate-limit/5xx, and notes the USPTO/PatentsView sunset 'soft-fails until reactivated.' It also states the output shape (grouped changes[], total_changes count, pipeworx:// URIs), providing complete transparency into what the agent will receive. No contradiction.

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 but every clause earns its place. It leads with the most useful part (user-question examples), then the core behavior, then sources and fallbacks, then parameter formats, then return structure, then the alternative tool. No fluff or repetition of schema fields. For a tool with this much behavioral nuance, the length is justified.

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?

Given 3 required params, complex multi-source fan-out, fallback logic, and no output schema, the description is remarkably complete. It covers input formats, source behaviors, failure modes, output structure, and usage boundaries (via the entity_profile redirect). The agent has all contextual information needed to decide when and how to invoke this tool correctly.

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?

The input schema already has 100% parameter descriptions, but the description adds substantial semantic value. It provides formats and examples for `since` ('ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y")') and clarifies `value` can be a ticker or zero-padded CIK. The `type` parameter's constraint ('Only company supported today') is reiterated. This enriches the schema's baseline with practical syntax guidance.

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 concrete example queries ('What's new with X', 'latest on Y') and states its core function: 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It then enumerates specific data sources (SEC EDGAR, GDELT→GNews fallback, USPTO), giving a precise scope. It also explicitly distinguishes itself from the sibling tool entity_profile, making its unique purpose unmistakable.

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?

This is exemplary. It gives clear conversational triggers (e.g., 'news on Tesla recently') and then says 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.' This explicitly tells the agent when NOT to use this tool and names the alternative. It also documents the fallback chain for news sources (GDELT preferred, GNews when rate-limited or 5xx), which is essential operational guidance.

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