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

Annotations already convey that the tool is destructive and not read-only, and the description adds useful behavioral context: this is not a one-shot edit but one that occurs through a persistent live session, implying statefulness and possible side effects beyond the single call. It does not contradict the annotations and adds meaningful non-schema information.

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?

Two tight sentences deliver the core action, the session-based behavior, and the key routing guidance without wasted words. The most important behavioral information is front-loaded before the parameter-preference note.

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?

Given the tool's complexity — multiple operation types, rich anchor forms, and a destructive annotation — the description is functional for selection but thin on operational context. It does not clarify the lifecycle of the live session, the role of ifContentHash, or what happens if collaboration is not enabled; the rich schema and output schema carry much of the load.

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?

The schema already documents four of six parameters, and the description reinforces the routing guidance by saying natural workspace names and document titles are accepted while internal identifiers are optional. However, it does not explain the purpose of ifContentHash or add much beyond the existing parameter descriptions; the complex operations structure is 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?

The description names a specific verb ('Apply... edits'), a specific resource ('Markdown Document'), and a distinguishing method ('anchored edits') and context ('persistent live session when collaboration is enabled'). This makes it clear that the tool is for directly modifying an existing document rather than merely suggesting, commenting, converting, or publishing it.

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 description gives a usage condition by saying edits happen 'through a persistent live session when collaboration is enabled', which helps an agent identify the enabling environment. However, it does not state when to prefer this tool over siblings like add_suggestion, convert_document, or create_article, nor does it explain what to do when collaboration is not enabled.

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