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

Beyond the annotations (readOnly, idempotent, etc.), the description discloses substantial behavior: it fans out to SEC EDGAR, GDELT→GNews fallback, and USPTO with a sunset note (PatentsView API sunset May 2025, soft-fails until reactivated). It also explains the return structure (changes[] grouped by source, total_changes, citation URIs) and the two accepted formats for `since`. 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?

The description is dense but each sentence carries information: source fallbacks, sunset risk, parameter formats, return structure, and alternative tool. The opening quote list ("What's new with X" etc.) is a bit verbose but serves as an NLP-friendly utterance list for matching. It's longer than a simple two-sentence summary but earns its place given 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?

Given there is no output schema, the description takes full responsibility for explaining the return format. It does so explicitly (changes[] grouped by source, total_changes, citation URIs). It also explains the multi-source behavior, fallback logic, and a soft-fail condition. With three required parameters and a complex backend, the description covers all necessary context for an agent to invoke the tool correctly.

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?

The input schema already covers 100% of parameters with descriptions (type enum, since format, value as ticker/CIK). The description adds extra guidance: the '30d' or '1m' recommendation for typical monitoring, and clarifies that `since` can be ISO date or relative shorthand. This goes beyond the schema, though not dramatically, so a 4 is appropriate.

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 opens with concrete user intents ("What's new with X", "latest on Y") then states the tool's function: a change feed for a company in a date window, executed in one parallel call. It clearly identifies the resource (company) and the scope (time window), and distinguishes itself from the sibling entity_profile by explicitly directing users there 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?

The description gives explicit usage direction: "Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window." It also explains the underlying source fan-out and fallback behavior (GDELT preferred, GNews on rate-limit/5xx), which helps the agent decide when this tool is appropriate. This meets the 'explicit when/when-not/alternatives' bar.

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