phases_agents_refresh_skills

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

With no annotations, the description carries the full burden. It implies a rebuild (likely a mutation that overwrites existing state) and hints at authorization via "racines autorisees", but never states whether existing data is destroyed, whether permissions are required, or if the operation is idempotent.

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?

A single front-loaded sentence with no filler or repetition. It is efficiently written, though the terseness comes at the cost of the missing details scored elsewhere.

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 mutating, no-annotation, no-output-schema tool, the definition leaves too much unsaid: what the rebuilt registry contains, the effect on existing skills, and what is returned. An agent cannot safely decide whether to call this.

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%: "today" is documented in the schema, but "root_ids" has no description. The phrase "racines autorisees" loosely signals that root_ids must be authorized roots, but adds no format, cardinality (max 16), or relationship detail beyond what the schema already enforces.

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 has a concrete verb ("Reconstruit") and object ("un registre"), but the object does not match the tool name: it says "registre" while the tool is about skills. Nothing distinguishes it from siblings like phases_agents_detect or phases_agents_list_skills, leaving the agent to guess what is actually being rebuilt.

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?

There is no when-to-use guidance, no prerequisites, and no mention of the sibling tools (detect/get_skill/list_skills/plan) that could be alternatives. The adverb "explicitement" hints the operation is deliberate but does not tell the agent when that is warranted.

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