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

The description goes far beyond the readOnlyHint/idempotentHint annotations by disclosing the fan-out to SEC EDGAR, GDELT→GNews fallback behavior, and the USPTO soft-fail due to API sunset. It also specifies output structure (changes[] grouped by source, total_changes, pipeworx:// citation URIs), which is valuable since no output schema exists.

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 example user queries and then systematically covers behavior, parameters, output, and alternatives. Every sentence contributes distinct information, and the structure is dense without being bloated. It is longer than minimal but appropriately sized for a tool with multi-source fan-out and 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?

For a fairly complex tool with no output schema, the description covers the essential behavioral contract: input formats, source behavior, fallback mechanisms, output grouping, and a pointer to the alternative entity_profile tool. It is sufficiently complete for an agent to select and invoke correctly without additional context.

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?

Input schema covers 100% of parameters, so the baseline is 3. The description adds meaningful guidance beyond the schema, such as concrete examples of `since` formats ('7d', '30d', '3m', '1y'), the recommendation to use '30d' or '1m' for typical monitoring, and clarification that `value` can be a ticker or CIK. This extra context 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 clearly identifies the tool as a change feed for a company over a time window, with concrete natural-language triggers like 'What's new with X' and 'latest on Y'. It distinguishes itself from entity_profile by contrasting windowed changes with static profiles, making sibling differentiation strong.

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 explicitly states when to use this tool ('change feed for a company in the last N days/weeks/months') and gives explicit alternative guidance: 'Use entity_profile instead when you want the static profile... regardless of window.' It also clarifies the intended user queries, making selection straightforward.

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