Fetch the bounded content of a validated skill by ID, rejecting arbitrary file paths. Provide root IDs, skill ID, and ISO date to return safe skill data.
Retourne le contenu borne d'un skill valide par identifiant. Aucun chemin libre n'est accepte.
| Name | Required | Description | Default |
|---|---|---|---|
| today | Yes | Date ISO YYYY-MM-DD injectee. | |
| root_ids | Yes | ||
| skill_id | Yes |
Changes observed during successful MCP inspections.
v0.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It hints at two behaviors — content is 'borne' (bounded) and only identifiers (no free paths) are accepted — but never explains the bound, what happens on an invalid/unknown skill_id, permission requirements, or the return shape.
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?
Two tight sentences with the core purpose front-loaded and no padding. It is efficient, though extremely sparse for a three-required-parameter tool.
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?
With three required parameters, no annotations, no output schema, and no explanation of root_ids or today, the description is too thin for an agent to call this tool confidently. The one behavioral constraint it does give ('aucun chemin libre') is not enough to cover the gaps.
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 only 33%: 'today' is documented in the schema while 'root_ids' and 'skill_id' are not. The description says lookup is 'par identifiant' but never explains what root_ids (1–16 ids) is for or why an injected 'today' is required, so it fails to compensate for the coverage gap.
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 ('Retourne le contenu ... d'un skill') and scopes it by 'identifiant', which separates it from the sibling phases_agents_list_skills (listing) without naming it. The qualifier 'valide' adds a validity condition, but no explicit sibling differentiation is given.
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 statement of when to use this tool versus phases_agents_list_skills, phases_agents_refresh_skills, or phases_agents_plan. 'Aucun chemin libre n'est accepte' is an input constraint, not usage guidance. The agent must infer the use case from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.