split_question

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

With no annotations at all, the description carries the whole burden and does well: it discloses atomicity ("one write"), marker inheritance for parts, that an `answer` settles a part as written, the record_in default of "Decisions", and that it returns the still-open parts with their new indexes. It omits what happens to the original question beyond "in its place", and says nothing about permissions or failure behavior.

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?

Purpose is front-loaded in the first clause before the detail, and every sentence carries real information (inheritance rules, answer handling, return value). It is a single dense sentence with stacked parentheticals, which costs some readability but not enough to be 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 mutation-style tool with no annotations and no output schema, the description covers the important semantics and even states the return value. But five of seven parameters are undocumented (including the whole `match`/`index` targeting mechanism) and the "remove" mode is never explained, leaving real gaps for an agent wiring up the call.

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 low (29%), so the description must compensate, and it does explain the `into` payload shape (text or { text, implementation?, answer? }), inheritance, `record_in` and its default, and the "tick" value of `mode`. However `ref`, `index`, `match`, `collection`, and the "remove" mode value are left entirely to 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 (split) and resource (an open question) plus the exact transformation: one question per decision, in place and order, in one write. It name-drops the sibling resolve_question as the behavioral analogue, so an agent can separate it from add_question or resolve_question without opening a 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?

The opening clause implies the trigger condition clearly (an open question that poses several decisions), and it points to resolve_question for the tick-mode behavior. There is no explicit when-not-to-use or statement of prerequisites (e.g. permissions on the initiative), so it stops short of full routing guidance.

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