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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower, yet the description still adds substantial context: the parallel fan-out to three sources, the GDELT→GNews fallback trigger conditions, and the USPTO PatentsView sunset with soft-fail behavior. It also discloses the return shape (changes[] grouped by source, total_changes, pipeworx:// URIs). No contradiction with 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?

Dense but every sentence earns its place: the leading query examples aid intent matching, the fan-out and fallback details set correct expectations, and the closing sentence routes to the sibling. It is front-loaded with user phrasing before the technical machinery, and the length is proportionate to the tool's complexity.

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?

Despite having no output schema, the description discloses the top-level return shape (structured changes[] grouped by source, total_changes count, pipeworx:// citation URIs) so the agent knows what to expect. It covers sources, failure modes, since formats, and the sibling distinction — complete for a high-complexity, multi-source read tool. The only minor gap is that fields inside a changes[] item aren't enumerated.

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 and the schema already documents type, since, and value. The description adds only a usage preset ('Use "30d" or "1m" for typical monitoring') and restates the since shorthand formats; this is marginal value, not substantial new meaning beyond the schema.

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?

States a specific verb and resource: 'change feed for a company in the last N days/weeks/months', backed by six natural-language query patterns. It distinguishes itself from the sibling entity_profile by explicit contrast (time-windowed changes vs static profile), and its multi-source scope (SEC/GDELT/GNews/USPTO) clearly separates it from recent_alerts.

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?

Explicitly names the alternative and the condition that selects it: 'Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.' It also prescribes a default window ('Use "30d" or "1m" for typical monitoring') and documents the fallback policy (GDELT preferred, GNews when rate-limited or 5xx).

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