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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds significant behavioral detail beyond these: parallel fan-out to SEC EDGAR, GDELT-to-GNews fallback (with conditions), and USPTO soft-fail due to API sunset, plus the return structure. This is exactly the kind of context annotations cannot convey.

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 and front-loaded with the core purpose, then details sources, fallbacks, and return format. While it includes multiple illustrative examples ('What's new with X' etc.) that are useful for NL matching, they add length. Overall, every sentence contributes value, but it is slightly longer than strictly necessary.

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?

Since there is no output schema, the description fully covers the return shape ('structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs') and explains edge cases like GDELT/GNews fallback and USPTO soft-fail. It also cross-references entity_profile, making the description complete for a tool of this complexity.

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 provides 100% coverage with descriptions for all three parameters, including the exact `since` formats (ISO date and relative shorthand) and examples for `value`. The description repeats the same `since` details but adds no new parameter semantics, so it meets the schema-heavy baseline of 3.

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 precisely defines the tool as a 'change feed for a company in the last N days/weeks/months' and includes concrete query examples. It explicitly distinguishes from sibling tool entity_profile, noting 'Use entity_profile instead when you want the static profile,' which makes its scope 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 clear usage context with natural language triggers ('What's new with X', 'latest on Y') and provides an explicit alternative: 'Use entity_profile instead ... regardless of window.' It also explains the source fan-out and fallback behavior, helping the agent decide when to invoke it.

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