verify

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

With no annotations, the description carries the full burden and does well: it discloses the internal procedure (removing precedents and re-asking the model, plus a random-removal control), the side effect that an explanation may be created for a held-out order, and the shape of the output (confidence drop, verdict, strength label, summary). It does not disclose cost/latency despite implying many model calls, which keeps it from a 5.

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?

Front-loaded with a one-line purpose, then process, then returns, then args — a logical order where each sentence adds information. The Args block is somewhat verbose and the line-wrapped style is a little awkward, but nothing is filler.

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 and no annotations, yet the description enumerates the returned fields and explains the comparison logic, which is enough to invoke and interpret results. What it omits (threshold for the true/false verdict, runtime cost of repeated model calls) is secondary but not negligible.

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 0%, so the description must compensate, and it documents all four parameters including the otherwise opaque "model" values ("fast" or "base") and what n_random counts. Minor gap: it does not say the two id parameters are mutually exclusive beyond the word "alternatively."

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 concrete verb+resource ("Check an explanation against the full model") and describes the actual mechanism (strip precedents, re-query, compare against random non-precedent orders). It clearly differs from explain/predict by being a post-hoc validation step, though it never explicitly names the siblings it should not be confused with.

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?

"explanation_id: id returned by explain. Preferred." plus "order_id: alternatively, a held-out order" gives explicit routing between the two entry paths, and "model: used only with order_id" states an exclusivity constraint. It lacks guidance on when verification is warranted versus simply calling explain, so not a 5.

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