Call any GHL endpoint

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

Annotations already indicate destructive and non-idempotent behavior, so the description adds useful context by noting that the same write/delete gates as dedicated tools apply and that all path/query/body fields are flattened. This goes beyond the structured annotations without contradicting them.

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 with no filler. The core action and the critical flat-argument behavior are front-loaded, and the important gate caveat is appended efficiently.

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?

For a highly generic dynamic endpoint tool, the description is reasonably complete: it explains the argument model, points to the schema-discovery sibling, and flags safety gates. It does not describe return values or error behavior, but those are inherently variable for 'any endpoint', so this is an acceptable gap.

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 descriptions already cover the parameters at 100%, but the description adds meaningful semantics: arguments must be flat with path, query, and body fields at top level, and users should consult ghl_describe_endpoint for the exact shape. This materially improves an agent's ability to build correct calls.

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 clearly states the action ('Execute any endpoint by tool name') and the resource (any GHL endpoint), and immediately distinguishes itself from the dedicated sibling tools by being a generic executor. The mention of a flat arguments object further specifies how the operation is performed.

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 implies a generic fallback use case but never explicitly says when to prefer this tool over a dedicated sibling endpoint. It references ghl_describe_endpoint for input structure and mentions write/delete gates, but stops short of stating 'use dedicated tools when one exists' or providing a clear when/when-not rule.

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