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

Annotations (readOnlyHint, idempotentHint, openWorldHint) already establish safety, but the description goes further by disclosing internal behavior: parallel fan-out to SEC, GDELT/GNews, and USPTO; GDELT preference with GNews fallback; and USPTO soft-fail due to PatentsView API sunset. It also mentions the return format (changes[], total_changes, citation URIs) beyond what annotations provide, giving the agent a clear mental model.

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 a single dense sentence, front-loaded with natural-language query examples, followed by the source fan-out logic and a clear pointer to an alternative tool. Every clause delivers essential information—sources, fallbacks, input format, output shape, and sibling distinction—without wasted words.

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 the tool's multi-source complexity and the absence of an output schema, the description adequately covers what it returns ('structured changes[] grouped by source + total_changes count + citation URIs') and how it behaves under failures (GNews fallback, USPTO soft-fail). It also clarifies that the operation is a single parallel call, which is critical for runtime expectation. No obvious gaps remain for practical use.

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 schema already provides full descriptions for all three parameters (type, since, value), and the description's examples ('2026-04-01', '7d', '30d', 'AAPL', '0000320193') mirror the schema text almost exactly. Since schema coverage is 100%, the description adds limited new parameter-level meaning, though it does reinforce typical usage ('Use 30d or 1m for typical monitoring').

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 explicitly states the tool provides a 'change feed for a company in the last N days/weeks/months' and frames it with concrete user queries like 'What's new with X' and 'updates on Acme'. It also distinguishes itself from the sibling tool entity_profile by comparing feed versus static profile, making its purpose unambiguous.

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 direct usage guidance: 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.' It also explains the fan-out strategy and fallback logic (GDELT→GNews on rate limits/5xx), which helps an agent decide when this tool is appropriate and what behavior to expect.

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