lancer_generation

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

No annotations, so the description carries the full burden and largely does: it discloses async/background execution, the run.log location under <cours>/work/, a progress-tracking mechanism, and a timing estimate (~1 min per 10 min audio). It omits failure/overwrite behavior and permission requirements, but the key operational traits are present.

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 core action is front-loaded in the first line, followed by parameter, logging, and timing notes. Reasonably sized with little waste, though parameter details could be organized more tightly against the schema.

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?

An output schema exists, so return values need no explanation. For a heavyweight no-annotation generation pipeline the description is adequate on behavior (async, log, timing) but incomplete on parameters and on prerequisites such as required inputs.

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 0%, so the description must compensate, yet it only explains `langue` (translation target, defaulting to course language, transcription authoritative). The other three parameters — date, cours, sujet — receive no semantics at all, leaving most of the schema undocumented.

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 ('Lance') and the exact pipeline resource ('chaîne transcription → plan → fiche/questions/cartes en arrière-plan'). An agent can immediately distinguish this generation trigger from siblings like detail_cours (progress) or fiche/cartes (artifact retrieval).

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 usage (background run, follow progress via detail_cours) but never states when to prefer this over alternatives or any preconditions (e.g., must the course/fichier exist first?). Progress-tracking pointer is useful but not explicit when-to-use/when-not guidance.

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