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

Beyond the annotations (readOnly, idempotent, openWorld), the description discloses important behavioral nuances: fan-out to multiple data sources (SEC EDGAR, GDELT→GNews fallback, USPTO), the specific fallback trigger (rate-limited or 5xx), and the soft-fail for USPTO due to PatentsView API sunset. It also states the return shape (structured changes[], total_changes, pipeworx:// citation URIs), which adds real transparency not available in 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 dense but every sentence serves a purpose: query examples front-load purpose, the fan-out details explain behavior, the `since` guidance helps parameter choice, and the entity_profile alternative gives exclusion context. The use of dashes and em-dashes creates clear separation, and the length is appropriate for a tool with multiple data sources and fallback logic. No filler or redundancy.

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 (three data sources, fallback logic, soft-fail, and no output schema), the description covers all essential aspects: what sources are queried, how fallback works, what inputs are accepted, what the return structure looks like, and when to use an alternative. It even mentions the 'in ONE parallel call' efficiency characteristic. This is a complete picture for an agent to select and invoke the tool correctly.

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 adds value by explaining the `since` parameter with concrete examples (ISO date '2026-04-01' vs relative shorthand '7d', '30d', '3m', '1y') and recommending '30d' or '1m' for typical monitoring. It also clarifies the `value` parameter accepts ticker or CIK, which is slightly more explicit than the schema. This pushes it above 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 multiple concrete query examples ('What's new with X', 'latest on Y') that make the tool's purpose unmistakable. It then states clearly: 'change feed for a company in the last N days/weeks/months in ONE parallel call,' and even distinguishes itself from sibling tool entity_profile by describing what each is for. This is a specific verb+resource description that fully differentiates from siblings.

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?

Provides explicit when-to-use context via natural language query mappings and gives a direct alternative: 'Use entity_profile instead when you want the static profile... regardless of window.' It also offers practical parameter advice ('Use "30d" or "1m" for typical monitoring') and explains the fallback chain, so the agent understands not only when but also how the tool adapts.

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