compare_834

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

With no annotations supplied, the description carries the full burden and does disclose real behavioral logic: full-file detection via the BGN08 indicator and the resulting flagging of potential unintended terminations, plus why that matters (coverage gaps). It does not state that the operation is read-only/non-mutating, nor what the report output looks like structurally, nor how mismatched-group or missing-file inputs are handled.

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 scope and comparison intent are front-loaded in the first clause, and the enumerated change categories are compact rather than prose. The second sentence is dense with jargon (BGN08 RX or 4) that could slow an agent, but every sentence carries information.

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?

There is no output schema, so the description does the work of describing the returned report by listing the change categories, which is largely sufficient for correct invocation. Gaps remain around output format/ordering, the PII toggle's effect on the report (only stated in the schema), and error behavior for cross-group comparisons.

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 coverage is 100%, so the baseline is 3, but the description adds genuine domain meaning beyond the schema — it explains how new_file is interpreted in terms of the BGN08 full-file indicator, which the schema's one-line "Later file, relative to EDI_834_DIR" does not convey. It adds nothing about old_file beyond ordering, which is already implicit in 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 ("Compare two 834 files") and then enumerates the exact change classes reported — members added/missing, coverages, tier and plan changes, begin-date and demographics. This makes it unmistakable that it is a diff tool rather than a validator (validate_834) or a single-file explainer (summarize_834).

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?

Gives clear framing for when to use it: two files for the same group, e.g. last week's vs. this week's, and explains the specific condition under which missing members become meaningful (new file is a full file, BGN08 RX or 4). It stops short of explicit exclusions — it never says what to do if the files span different groups, or when to prefer summarize_834 instead.

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