Smart Rules

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

With no annotations, the description carries the full burden, and it does well: it discloses the scan signals (long sentences, Arabic chars, ZWNJ, Latin punctuation, etc.), that rules are ordered by signal weight, that each rule carries a `why` field, and that Layer 1 is always the task-type rule_pack. It omits any note on cost/latency, determinism, or whether re-running yields identical output, so it falls just short of 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?

It is front-loaded with a one-line summary before the detail, and the sentence count is proportionate. The parenthetical signal list ('bureaucratic fossils', 'cliches, repetition, ...') is slightly decorative but does carry real information about what gets scanned.

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?

An output schema exists, so return values need not be explained, and the description adequately covers the tool's adaptive behavior, ordering, and the `why` evidence field for a moderate-complexity tool. The gap is the required `task_type` parameter, whose accepted values remain undefined anywhere, which matters because it determines Layer 1.

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 0% and the description never explains the three parameters. `task_type` is required and evidently drives the Layer 1 rule_pack, but no valid values or semantics are given; `max_rules` (default 60) is never mentioned at all. Only `text` is loosely implied to be the Persian text that gets diagnosed.

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 states a concrete two-stage action (diagnose Persian text, then build a tailored deep-edit checklist) and explicitly positions itself against the sibling `deep_rules` ('Smarter than deep_rules: instead of a fixed checklist...'). An agent can tell what this produces and how it differs from the fixed-checklist alternative without opening any schema.

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?

It makes the selection condition against `deep_rules` fairly clear: use this when you want rules pulled for the risk signals actually present rather than a fixed checklist. It also states the intended workflow ('any agent runs the edit -> review loop itself'). However it never states explicit when-not conditions or names other siblings (e.g. `rule_pack`, `mechanical_pass`) as alternatives, so routing is implied rather than spelled out.

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