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

The description goes beyond annotations by detailing multi-source fan-out, GDELT→GNews fallback conditions, USPTO soft-fail due to API sunset, and the output shape (changes[], total_changes, citations). This gives a realistic picture of external dependencies and non-determinism, complementing the readOnly/idempotent hints.

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 packs substantial operational detail into a few sentences, front-loading the core purpose and then layering source details, fallback logic, and output format. The user-query examples add length but improve discoverability, and no sentence is redundant.

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 the return structure and citation URIs. It also explains data sources, fallback behavior, parameter formats, and the alternative tool, covering all needed context for a complex multi-source API tool.

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 documents all three parameters with 100% coverage, including accepted formats for `since` and examples for `value`. The description repeats the `since` format but adds no new semantic information beyond what the schema provides, so it stays at baseline.

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 real-world query examples and then defines the tool as a 'change feed for a company in the last N days/weeks/months in ONE parallel call.' It explicitly names the underlying data sources (SEC, GDELT/GNews, USPTO) and contrasts with entity_profile, making the 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?

It explicitly directs users to entity_profile when they need a static profile instead of a time-windowed feed, which is a clear 'use instead' instruction. The examples also imply the tool is for recent-change lookups, covering typical use cases. No other sibling alternatives are mentioned, but this is sufficient for the core distinction.

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