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

The annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds significant behavioral context: parallel fan-out to multiple sources, GDELT→GNews fallback, USPTO PatentsView API sunset with soft-fail, accepted date formats with examples, and the output structure including pipeworx:// citation URIs. No contradiction with annotations.

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 front-loaded with user-facing query examples that immediately convey purpose. The technical details about sources and date formats follow logically. While fairly dense, every sentence adds value; no filler. Could be slightly shortened by removing the parenthetical about PatentsView, but acceptable.

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 complexity (multi-source, fallback, date parsing) and the absence of an output schema, the description covers the key inputs, sources, and output structure (changes[], total_changes, URIs). It doesn't detail error handling or pagination, but the annotations (idempotent, read-only) reduce risk. Adequate for effective 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?

Schema coverage is 100%, so baseline 3. The description adds value by explaining the semantics of each parameter: 'since' accepts ISO date or relative shorthand with examples and a recommended default ('30d' or '1m'), 'type' is constrained to 'company', and 'value' can be ticker or CIK. This goes beyond the schema 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 concrete example queries ("What's new with X", "latest on Y") that make the tool's purpose immediately clear. It explicitly states it's a change feed for a company over a time window, lists the data sources (SEC EDGAR, GDELT→GNews, USPTO), and distinguishes itself from the sibling tool entity_profile.

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 explicit when-to-use guidance via the example query patterns. It also provides a direct when-not-to-use statement: 'Use entity_profile instead when you want the static profile regardless of window.' It explains the fallback behavior between GDELT and GNews, and mentions the USPTO soft-fail condition.

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