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

Although annotations already declare destructive=true, idempotent=true and openWorld=false, the description adds the behavior an agent cannot get from them: which fields survive an edit, that null/[] clears classification arrays, that rewording preserves history and emits a stale-evidence warning, and that no Scan is launched. That is real added context for a mutation tool.

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 the core action and preservation semantics, and each sentence carries information for a 9-parameter mutation tool. It is dense to the point of stacking several rules per sentence, but there is no 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?

For a mutation tool with rich annotations and a real output schema, the description covers the essentials: prerequisites, side effects, history implications, sibling routing, and a return summary. Nothing an agent needs to call it correctly is absent.

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 78% and the schema already documents the null/[] vs omission rule per field, so much of the description's parameter prose is a restatement. It does add value by synthesizing the anyOf constraint into 'requires at least one editable field' and by noting regions fall back to scan defaults then Global, which is easy to miss in 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 and resource (edit an active question) and enumerates exactly what is editable: text, category and assignments. It also names the preserved invariants (ID, enabled state, omitted fields), which is what distinguishes it from create_prompt, retire_prompt and reactivate_prompt in the sibling list.

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?

Gives prerequisites ('Requires at least one editable field'), routes the retired-question case explicitly to reactivate_prompt, and points to get_scan_config and list_prompts for the IDs/definitions the caller needs. An agent can pick this tool over its siblings without further inference.

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