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

No annotations, so description carries full burden and does so richly: exact credit costs (1/5/+1), paid-plan restriction for hybrid_chapters, required scope generate:ai_courses that admin:* does NOT grant, source-type constraints, and rate limits (2 running, 10/hour). This is exceptional disclosure of cost, permissions, and throttling for a mutation tool.

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?

Dense but front-loaded with the cost and job-polling model first, then permissions, then constraints. Every sentence earns its place, though the credit-cost clause is somewhat packed and takes a second read.

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 12-param async generation tool with no output schema, the description supplies the return contract (job_id to poll), cost model, permissions, source-type rules, and rate limits—everything an agent needs to call successfully. Remaining minor params are low-risk optional knobs.

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 50%, and the description compensates with dispatch rules: video_url imports public YouTube/Vimeo/Loom while every other type needs a file already on HiveLearn storage with external URLs rejected, and include_recap_video costs +1. Still some params (brand_intensity, content_depth, style_preset, quiz_questions_per_chapter) get no added meaning, but the critical routing logic is covered.

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 (Generate) and resource (full course with AI), and immediately distinguishes itself from hivelearn_create_course by noting it returns a job_id to poll. An agent can tell this is the async AI-generation tool versus the manual course-creation siblings.

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?

Clear usage context: confirm with the user before calling, and it points to hivelearn_get_ai_job for polling. It implies when to use it (full AI-generated course) but doesn't explicitly contrast with hivelearn_create_course_outline or manual creation paths.

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