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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the live nature, the multi-tier source chain with 'first hit wins' logic, the freshness threshold for the is_stale flag (older than 48h), the data_source_pending condition, and the 15-minute cache. This is exceptionally transparent about how the tool behaves under various data availability scenarios.

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 a dense single paragraph that front-loads the core purpose and metric list, then elaborates on sources, freshness, and fallbacks. Each clause adds meaningful information, but the structure could be improved by using list formatting or shorter sentences. The content earns its place, though it reads as slightly run-on.

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 simple one-parameter data tool with no output schema, the description covers all critical operational context: source chain, data recency expectations, stale flag semantics, fallback behavior, and caching. It does not describe the exact response shape or field names beyond the metrics listed in parentheses, but given the tool's simplicity and the absence of an output schema, it is sufficiently complete.

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 schema already documents the single 'ticker' parameter with 100% coverage, so the description need not repeat its format. It does not add details about ticker formatting or constraints, but the parameter is simple and self-explanatory. The description's focus on output semantics (borrow cost components) indirectly clarifies what the ticker is used for. Baseline 3 is appropriate since the schema does the heavy lifting.

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 the tool provides securities-lending borrow cost metrics (annualized fee %, rebate, utilization, shares available) in a LIVE context. It distinguishes itself from sibling tools by specifying the source chain and explicitly pointing to /intel/borrow_cost_history for daily series and /intel/short_interest as a fallback, making its unique purpose unambiguous.

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 provides explicit usage guidance: it names the alternative tool for historical daily series ('Use /intel/borrow_cost_history for the daily series'), explains the fallback to /intel/short_interest when data_source_pending=true, and describes the cache behavior (15-min). This clearly communicates when to use this tool versus its siblings and what to expect under different data conditions.

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