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

While annotations already declare readOnly/idempotent/destructive safety, the description adds substantial behavioral detail: fan-out to multiple sources, the GDELT→GNews fallback on rate-limit/5xx, and a soft-fail for USPTO due to the PatentsView API sunset. It also discloses that it returns grouped changes with citation URIs and executes in one parallel call.

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 but every sentence contributes: opening intent examples, source enumeration with fallback/soft-fail details, parameter formats, return structure, and an alternative tool pointer. It is front-loaded with use cases, and no word is wasted.

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 (3 params, no output schema, multiple sources), the description covers the core invocation surface well: what sources are queried, what `since` accepts, what is returned (changes[] grouped by source + total_changes + citation URIs), and when to use an alternative. It lacks explicit detail on error behavior or empty results, but the provided guidance is sufficient for typical 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 is 3. The description goes beyond the schema by elaborating `since` formats with concrete examples ('7d', '30d', '3m', '1y'), recommending '30d'/'1m' for typical monitoring, and clarifying how `value` (ticker or CIK) is used across the different data sources. This extra guidance justifies a 4.

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 clearly identifies the tool as a change feed for a company over a recent window, with concrete intent examples ('What's new with X') and explicit sources (SEC EDGAR, GDELT/GNews, USPTO). It explicitly distinguishes itself from the sibling entity_profile tool by contrasting dynamic changes vs. static 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 provides explicit usage guidance, including example queries that indicate when to use the tool and a direct recommendation: 'Use entity_profile instead when you want the static profile... regardless of window.' It also gives practical advice for the `since` parameter ('Use "30d" or "1m" for typical monitoring').

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