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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description reveals a crucial two-step behavioral pattern: calling with field_type='dropdown' and no options returns needs_confirmation with AI-suggested options, requiring a second call with confirm=true. This is essential non-obvious behavior that the agent must know to avoid incorrect usage. No contradiction with annotations.

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 appropriately sized for the tool's complexity. It front-loads the core purpose, then explains field types, and ends with a critical workflow note. Every sentence adds value—the confirmation workflow would be missing otherwise. It is not overly verbose.

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 5 parameters, no output schema, and minimal annotations, the description delivers complete operational context. It covers return behavior (needs_confirmation with suggested options), the necessity of user approval, and the final creation call. This is sufficient for an agent to use the tool effectively without guessing.

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 description adds significant meaning to parameters beyond the schema. It explains field_type values ('text' for free text, 'dropdown' for lookup/picklist), clarifies that options should be omitted to get AI suggestions, and specifies confirm is 'Set true to create even a dropdown with the given options.' This compensates for the 60% schema coverage and directly informs parameter usage.

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 opens with a specific verb and resource: 'Add a custom column to contacts or companies.' It clearly distinguishes from sibling tools like add_contacts or create_contact by focusing on custom field creation. The mention of field_type and the dropdown workflow further clarifies its unique scope.

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 explicit when-to-use guidance: 'when the user wants a lookup-style column... you MUST first ask whether they want it as a lookup (dropdown) or a normal text field.' It also provides a detailed conditional workflow for dropdown fields, including the two-call confirmation process. This goes beyond generic context and directly helps the agent decide and act.

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