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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), and the description adds behavioral context beyond them: 'Uses REAL metadata from the KB (actual field names, method signatures)' and the hard dependency on a prior get_object_details call. It does not detail the return payload or failure modes, but generation semantics are consistent with the read-only, idempotent annotations — no contradiction.

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 content is front-loaded — the WHEN frame and purpose come first, followed by triggers, glossary, and the precondition. Every clause earns its place; the trigger list is slightly long with some French/English duplication, but that redundancy is arguably useful for matching a multilingual agent's input. It is dense but not bloated.

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 tool with no output schema and five distinct generation modes, the description covers the essential gaps: when to use it, what it produces, what each templateType value means, and the required upstream call (get_object_details). The one omission — describing the exact return format — is minor because the generated code is self-evidently the output.

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 100%, giving a baseline of 3, but the description goes beyond the bare value list by defining each templateType: 'coc' = Chain of Command class, 'table_extension' = extend table with fields/methods, 'event_handler' = pre/post event handler, 'job' = runnable class, 'find_method' = find/exist pattern. This vocabulary expansion is exactly the kind of meaning the schema alone does not provide.

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 states a specific verb and resource — 'generates ready-to-use X++ code' — scoped to 'writing an extension or customization.' It differentiates from siblings like generate_xpp_form, generate_query, and generate_unit_test by enumerating its five template types (coc, table_extension, event_handler, job, find_method), so an agent can select it without inspecting other schemas.

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 'WHEN:' frame plus the trigger phrases ('génère un CoC', 'crée une extension', 'generate extension', 'write a CoC class') give concrete, multilingual conditions for invocation. It also enforces a workflow precondition: 'ALWAYS call get_object_details first to verify the object exists.' It stops short of naming sibling alternatives or stating when not to use the tool, which keeps it a step below a 5.

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