Modify contact details in GLPI by passing only the fields to change. Restore a deleted contact by setting is_deleted to 0.
Met à jour un contact. Passer uniquement les champs à modifier. Exemples de champs : name, firstname, contacttypes_id, phone, mobile, email, comment Pour restaurer un contact mis à la corbeille : {"is_deleted": 0}
| Name | Required | Description | Default |
|---|---|---|---|
| contact_id | Yes | ||
| update_fields | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose two important behavioral traits: partial update semantics and how to restore a deleted contact. It still omits permissions, reversibility, side effects, and response behavior for this 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?
The description is short and front-loaded, leading with the core action and the partial-update rule before examples. The example JSON is useful, though the formatting could separate the restoration example more cleanly.
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 two-parameter mutation tool with no annotations, no output schema, and 0% schema coverage, the description covers the basic purpose, partial-update behavior, example fields, and a restoration case. It still leaves the required contact_id parameter and the tool's response or permission requirements undocumented.
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 0%, so the description must compensate. It lists example update_fields keys and shows a special is_deleted: 0 restoration payload, which adds meaning for update_fields. However, contact_id is not documented at all, and the update_fields schema remains open-ended.
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 clearly states a specific verb and resource: 'Met à jour un contact' (updates a contact). It distinguishes itself implicitly from create_contact and delete_contact by being the update operation, but it does not explicitly name sibling alternatives or contrast scopes.
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?
It gives useful partial-update guidance ('Passer uniquement les champs à modifier') and a restoration scenario using is_deleted: 0. However, it does not say when to prefer this tool over alternatives such as create_contact, delete_contact, or other update tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.