ghl_course_create

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

Annotations already flag this as a non-readonly, non-idempotent, open-world write. The description adds value beyond that: required OAuth scope, the exact endpoint and API version header, token type, and an explicit list of fields the API will reject ('locationId, userId, id, originId, source, and processing are not accepted'). It doesn't say what the response contains, but the mutation semantics are well covered.

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 create intent is front-loaded, but the text carries template noise ('COURSES API —', the phantom productId note, 'source: v3/courses-v3.json') that doesn't help an agent invoke this tool, padding out what should be two or three sentences.

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 2-parameter create with a nested body and no output schema, the description covers auth, scope, endpoint, and rejected fields — enough to call it correctly. Only the shape of the successful response is left unspecified, which is a minor gap given no output schema exists.

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%, so the baseline is 3. The description adds the exclusion list (useful) but its only param-level claim — that {productId} is the course id — refers to a path parameter that does not exist in this tool's schema, which is mildly misleading rather than additive.

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 ('Create a course in the location') right after the header, so the operation is unambiguous and distinguishable from siblings like ghl_course_update or ghl_course_list. The leading line about the '{productId} path parameter' is a template artifact that doesn't correspond to any parameter in the schema, which slightly muddies an otherwise clear statement.

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 prerequisites (Sub-Account/location token, courses.write scope) which tells the agent when it can call it, but never contrasts with the other course or product creation tools (e.g. ghl_course_import, ghl_product_create) or states when not to use it.

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