ghl_contact_create_task

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

Annotations provide minimal behavioral hints (destructiveHint=false, etc.). The description adds some parameter constraints but does not disclose side effects, error behavior, or return value. Historical regression notes add context but do not improve transparency about the tool's behavior.

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 overly verbose, beginning with regression notes that are not essential for an AI agent to use the tool. The core information (purpose, endpoint, requirements) is present but buried in unnecessary detail.

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 nested body object and no output schema, the description provides the endpoint, OAuth scopes, and required fields. It lacks information on return values, error scenarios, and how the tool integrates with related actions like task retrieval or update.

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 100%, and the description adds meaningful detail: it clarifies required fields, specifies ISO 8601 format for dueDate, and notes that completed:false is required even if counterintuitive. This provides value beyond 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 states 'Create Task' and provides the endpoint, making the action clear. However, the initial regression notes are verbose and could confuse an AI agent. The tool name itself is descriptive, and while it is one of several contact task tools, no explicit distinction from siblings is provided.

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 specific requirements for the body fields (title, dueDate, completed must be present, dueDate must be ISO 8601) and mentions OAuth scopes. However, it does not guide when to use this tool versus update or delete, nor does it provide exclusions or alternatives.

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