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

With no annotations, the description carries full burden and delivers: primary vs fallback data sources, refresh lag requiring as_of checks, 1h cache, and the specific fields returned. It even highlights the squeeze-watch interpretation (rising fee + utilization), which is valuable behavioral context beyond a simple read.

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 organized, front-loading the main purpose and then adding necessary details about sources, fallback, lag, and cache. Each sentence contributes useful information, though the string of clauses in the middle could be more readable. Still, it is appropriately sized for 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 the tool's complexity and absence of an output schema, the description covers data source, fallback, time range, lag/cache, and how to interpret the data. It misses explicit parameter format details (start/end/limit), which slightly reduces completeness, but overall it provides strong contextual grounding 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?

Schema description coverage is only 25% (only ticker has a minimal description). The description adds context about time windows but does not clarify start/end format or limit semantics, and introduces ambiguity: says 'max 365-day window' while schema allows limit up to 2000, leaving the relationship between time window and row limit unclear. This does not adequately compensate for the low schema coverage.

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 returns daily securities-lending borrow-cost history for one ticker from a specific warehouse. It explicitly contrasts with the live snapshot tool by saying 'use /intel/borrow_cost for the live snapshot', thereby distinguishing from the sibling tool tengu_v3_intel_borrow_cost. The scope, source, and data fields are all specified.

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 guidance: default 90-day coverage, max 365-day window, fallback to implied-vol when primary data is missing, and lag/cache warnings. It names the alternative tool for live snapshots, making when-to-use vs when-not-to-use clear.

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