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

Annotations already set readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds substantial behavioral context beyond these: fan-out to SEC EDGAR, GDELT→GNews fallback, USPTO (with noted soft-failure), and the structured return format (changes[] grouped by source, total_changes, citation URIs). This level of detail helps the agent understand side effects and limitations without contradicting 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 relatively long but every sentence adds meaningful detail. It front-loads the purpose with common user queries, followed by source details, parameter formats, and sibling guidance. While it could be slightly more concise, the structure is clear and easy to scan. The length is justified by the tool's complexity (multiple sources, fallback logic).

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 lack of an output schema, the description compensates by stating the return structure (changes[] grouped by source, total_changes count, citation URIs). It covers all parameters, usage context, source behavior, and fallback logic. The only minor gap is that it does not elaborate on the exact shape of each change object, but the overview is sufficient for most agents to decide whether to invoke the 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?

With 100% schema coverage, the baseline is 3, but the description adds extra meaning: for 'since', it explains acceptable formats (ISO date, relative shorthand) and recommends a typical value ('30d' or '1m'). For 'value', it provides examples (ticker or CIK). For 'type', it clarifies that only 'company' is supported. This contextual guidance 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 immediately lists example user queries ('What's new with X', 'latest on Y'), making the tool's purpose unmistakable. It clearly states it returns a change feed for a company in a time window, fanning out to multiple sources. The explicit differentiation from sibling tool entity_profile ('Use entity_profile instead when you want the static profile') ensures the agent can distinguish it correctly.

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 provides clear context for when to use the tool (for recent changes/news) vs. entity_profile (static profile). It gives example queries and explains the multi-source fan-out and fallback behavior (GDELT→GNews). While it does not list explicit when-not-to-use scenarios, the sibling distinction and parameter guidance ('Use "30d" or "1m" for typical monitoring') are sufficient for most cases.

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