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

Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=true; the description adds real context beyond them — the post is public immediately under the caller's name, may be short-circuited by duplicate detection, and involves a confirmation prompt plus an owner approval wait. It stops short of saying what a successful call returns (question id/URL) or whether the post can be undone, which matters given destructiveHint=true and the absence of an output schema.

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 primary action is front-loaded in the first sentence and each subsequent sentence covers a distinct decision point (duplicate, similar, confirmation, approval) with no filler. Minor ambiguity remains in "you can switch that off for this tool" and the separate "waits for the owner's approval" sentence, which reads as a second gate without stating how it relates to the confirmation prompt.

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?

With no output schema, the description does take on return-shape responsibility and names the two non-success statuses, which is the information an agent most needs to branch on. The remaining gap is the success case and error/permission behavior for a write tool that publishes publicly.

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 both parameters are already documented, and the description goes further by explaining the practical consequence of skip_duplicate_check: similar matches block the ask unless you either answer an existing question or re-invoke with the flag. That is meaningful behavioral meaning layered on top of the schema rather than a restatement.

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?

"Add a new public question to Quora" states a specific verb (add), resource (question), and visibility scope (public), and "under your name" identifies the authoring identity. This clearly separates it from read-side siblings such as get_question and search_questions.

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 gives concrete branch-level guidance for the duplicate cases: an existing identical question is returned as status exists, and similar matches mean nothing was asked, so you either answer one of them or retry with skip_duplicate_check. It does not explicitly tell the agent to pre-check via search_questions, but the in-flow routing is unusually clear.

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