set_extension

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

Annotations already provide idempotentHint=true and safety info. Description adds that metadata persists in Microsoft Graph, but does not disclose additional behavioral traits beyond annotations. Minimal added value.

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?

Description is two concise sentences, front-loaded with the main action and benefit, with no superfluous information.

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?

Despite rich annotations, the description omits parameter details for list_id and task_id. For a tool with 5 parameters, the description is adequate but not fully complete.

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?

Only 60% schema coverage; key parameters list_id and task_id lack descriptions in both schema and description. Description does not compensate for missing parameter meaning.

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?

Description clearly states the tool creates or updates an open extension on a task (upsert), specifying verb and resource. It distinguishes from sibling tools like delete_extension and list_extensions.

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?

Description implies usage for attaching arbitrary JSON metadata to a task, but does not explicitly mention when to use vs alternatives like list_extensions or delete_extension, nor provide exclusions.

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