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

The description adds substantial behavioral detail beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint). It reveals the fan-out to multiple sources (SEC EDGAR, GDELT→GNews fallback, USPTO), the fallback logic (GDELT preferred, GNews when rate-limited or 5xx), and a known limitation (USPTO soft-fails until PatentsView API is reactivated). It also describes the return structure (changes[] grouped by source + total_changes + citation URIs), giving the agent a complete mental model of what happens.

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 earns its place. It opens with user-facing query examples, then explains sources, fallbacks, parameter formats, return object, and an alternative tool in a logical flow. Despite its length, there is no repetition or fluff; the structure front-loads the core purpose and then provides necessary operational details.

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?

The tool has moderate complexity (multiple data sources, fallback logic, date-range input, no output schema). The description fully covers this: it states the input format, source behavior, fallback rules, output shape (changes[] grouped by source, total_changes count, citation URIs), and the alternative tool. Given the lack of an output schema, the description's explanation of the return value is essential and complete.

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 elaborating the 'since' parameter: it accepts ISO dates ('2026-04-01') or relative shorthand ('7d', '30d', '3m', '1y') and recommends '30d' or '1m' for typical monitoring. It also clarifies 'value' as ticker or zero-padded CIK with an example, enriching the schema definitions. This extra guidance justifies a score 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 states a specific verb+resource+scope: 'change feed for a company in the last N days/weeks/months in ONE parallel call' with concrete examples ('What's new with X'). It also distinguishes from sibling 'entity_profile' by contrasting the dynamic change feed with the static profile, making the tool's 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?

Explicit guidance is given: 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.' This names the alternative tool and specifies when to choose it. Query examples like 'updates on Acme' illustrate appropriate use cases, providing clear context for when to invoke this tool.

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