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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive intent, but the description adds valuable behavioral context beyond them: fan-out to SEC EDGAR, GDELT/GNews fallback mechanism, USPTO soft-fail due to PatentsView API sunset, and the return structure (changes[], total_changes, citation URIs). This helps the agent anticipate real-world behavior like rate-limit fallbacks.

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 appropriately sized given the multi-source tool's complexity. It is front-loaded with user-centric query examples, followed by source details, parameter syntax, and the alternative tool. Some may find it a wall of text, but every sentence contributes necessary information, so it earns its place.

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 there is no output schema, the description compensates well by describing return values (structured changes[] grouped by source, total_changes count, and pipeworx:// citation URIs). It also covers fan-out sources, fallback behavior, and the differentiation from entity_profile. It doesn't detail the exact fields inside changes[], but this is acceptable for a feed tool with no output schema.

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 description coverage is 100%, so the baseline is 3. The description adds extra semantic value by elaborating the `since` parameter with supported formats (ISO date or relative shorthand like '7d', '30d') and recommending '30d' or '1m' for typical monitoring. It also reiterates `value` as ticker or CIK, but the main additive value is for `since`.

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 defines the tool as a 'change feed for a company in the last N days/weeks/months' with concrete query examples like 'What's new with X' and 'news on Tesla recently'. It explicitly distinguishes itself from entity_profile by directing users seeking static profiles to that sibling tool, satisfying the sibling-differentiation criterion.

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?

It provides explicit when-to-use guidance via query patterns and the 'ONE parallel call' efficiency note. It also gives a clear when-not-to-use instruction: 'Use entity_profile instead when you want the static profile... regardless of window.' This is a direct alternative recommendation.

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