Microsoft MCP

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Delete a contact' implies a destructive mutation, but it fails to specify whether deletion is permanent or reversible, what permissions are required, if there are side effects (e.g., cascading deletions), or what the response looks like. This is inadequate for a destructive operation with zero annotation coverage.

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 description is extremely concise at three words, with no wasted language. It is front-loaded and to the point, though this brevity contributes to its inadequacy in other dimensions. Every word earns its place by stating the core action.

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 destructive nature, lack of annotations, no output schema, and schema with 0% description coverage, the description is severely incomplete. It does not address critical aspects like safety, permissions, return values, or parameter meanings, making it inadequate for safe and effective use by an AI agent.

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 input schema has 0% description coverage, with two required parameters (account_id and contact_id) documented only by titles. The description adds no information about these parameters—it does not explain what an account_id or contact_id is, their format, how to obtain them, or their relationship. This fails to compensate for the schema's lack of descriptions.

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 'Delete a contact' is a tautology that merely restates the tool name without adding specificity. It does not clarify what constitutes a 'contact' in this context or distinguish this tool from sibling deletion tools like delete_email, delete_event, or delete_file. While the verb 'delete' is clear, the resource 'contact' lacks contextual definition.

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 provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., needing an existing contact), exclusions, or comparisons to sibling tools like update_contact or search_contacts. There is no indication of when deletion is appropriate versus modification or retrieval.

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