ghl_conversation_ai_update_agent_working_hours

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

Annotations declare a non-read, idempotent, non-destructive PUT, but they cannot express the crucial replace-vs-merge semantics, which the description states explicitly ('omitted fields are not preserved') — this is exactly the payload-loss risk an agent must know. It also adds the 404 failure mode, the required OAuth scope (conversation-ai.write), and the endpoint/version, none of which the annotations convey.

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?

Four tight lines, each carrying a distinct load-bearing fact: replace semantics, 404/create fallback, endpoint, and auth scope. The destructive-ish warning about omitted fields is front-loaded where the agent will see it first.

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 mutation tool with a large nested request body, the description covers the highest-risk unknowns: non-merge replacement behavior, the missing-resource error path, and the required scope. No output schema exists, so no return-value description is owed.

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 description coverage is 100% and the deeply nested body schema already documents every field, so the description only needs to add replace semantics at the top level, which it does. It adds nothing field-specific beyond that, so the baseline of 3 applies.

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?

States a specific verb and resource ('Update... working-hours configuration for an AI agent') and immediately disambiguates the semantics as a full replace rather than a patch. It also names the sibling create endpoint for the missing-configuration case, so an agent can distinguish it from the get/create/delete working-hours siblings in this namespace.

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?

Gives a clear precondition: 404 when no config exists, so use the create endpoint first. That covers the main when-not case. It does not mention the read (get_agent_working_hours) or delete siblings, so the routing is strong but not exhaustive.

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