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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint false), the description discloses rich behavioral details: it fans out to multiple external sources in parallel, includes a fallback chain, notes the PatentsView API sunset soft-fail, and details the return structure (changes[] grouped by source, total_changes, citation URIs). This gives the agent a clear mental model of execution behavior.

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 well-organized. It front-loads user intents, then gives the core function, source fanout details, parameter format guidance, return shape, and an explicit alternative — all in one coherent block. Every sentence adds value; no fluff or repetition.

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 tool with no output schema, the description fully covers the return format (changes[] grouped by source, total_changes count, citation URIs). It also covers source fallback, soft-fail conditions, and when not to use the tool. Combined with high schema coverage and clear annotations, the context is complete for agent decision-making.

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 the description need not repeat parameter basics. However, it adds valuable semantics: 'since' accepts ISO or relative shorthand with examples, 'value' accepts ticker or zero-padded CIK, and it recommends '30d' or '1m' for typical monitoring. This exceeds the schema-only information.

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 states this is a change feed for a company over a time window, with a specific verb ('change feed') and concrete sources (SEC EDGAR, GDELT→GNews, USPTO). It distinguishes itself from sibling tool entity_profile by explicitly directing users to that tool for static profiles.

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 examples ('What's new with X') and an explicit alternative: 'Use entity_profile instead when you want the static profile... regardless of window.' Also explains fallback behavior (GDELT preferred, GNews on rate limit/5xx), leaving no ambiguity about when this tool is appropriate.

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