check_duplicates

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

No annotations are provided, so the description carries the full burden. It usefully discloses a state-changing side effect ('a match sets the bill to exception'), which is genuine behavioral value, but it omits permissions needed, reversibility, and what happens/returns when there is no match.

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?

Two tight sentences with zero filler, and the core action is front-loaded before the side effect. It could be slightly richer, but nothing here is wasteful.

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 one-parameter tool with no output schema and no annotations, the description covers the action and one outcome (match → exception) but is silent on the no-match case and the return value. Adequate but with a visible gap.

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?

Only one parameter (bill_id) with 100% schema description coverage, so the schema already documents the input fully. The description adds no format, source, or semantics beyond what the schema provides; baseline 3 is appropriate for a single fully-documented parameter.

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 (check) and resource (a bill against the vendor's earlier bills), which is well beyond a tautology. It is distinguishable from read-only siblings like get_bill or match_invoice, though it never explicitly names which sibling handles the non-duplicate path.

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?

Usage is implied by the phrasing (run this to detect duplicate bills from the same vendor), but there is no explicit when-to-use, when-not-to-use, or alternative tool named. An agent must infer the trigger condition from the description alone.

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