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

Annotations already say readOnlyHint=true, but the description goes further and matches it precisely: 'Nothing is written', plus it explains the return content (allowed?, which statement decided, all statement evaluations) and discloses cost/rate behavior (1 request plus 1 per looked-up item). This is exactly the extra context annotations cannot provide.

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-loads the core definition, then consequences, then required inputs, then cost, then the cheaper alternative. Four dense sentences with no filler despite covering a complex tool.

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?

Detailed enough for an 11-param, multi-mode tool: it explains outcome, output shape, permissions, request cost, and an alternative approach. An output schema exists, so the description correctly stops short of enumerating return fields.

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% with 11 params, and the description still adds relational meaning beyond it: itemId is tied to update/delete/restore and supplies the old state, while new/patch/merge are framed as alternative write descriptions. Not exhaustive across all 11 params, but meaningfully additive.

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 (dry run / test) and resource (a write against a list's write rules), and distinguishes intent from siblings: this evaluates rules without writing, versus create_item/update_item which actually mutate. The parenthetical clarification of candidate vs saved rules sharpens the scope.

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?

Tells the agent what it needs (describe the write with itemId and new/patch/merge), what permission is required (update on the list), and names an alternative path (JSONPad docs server's check_write_rules) for syntax-only checks with no live data. No explicit 'do not use for X' exclusion, but routing is clear.

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