Update an existing supplier by sending only the fields to change, so you can modify supplier details without resending the full record.
Modifica un fornitore: passa solo i campi da cambiare.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| data | Yes | ||
| company_id | No | Azienda su cui operare. Default: FIC_COMPANY_ID o l'unica azienda del token |
Changes observed during successful MCP inspections.
v0.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations supply only idempotentHint=true, so the description must carry most of the behavioral load. The partial-update sentence usefully implies that unspecified fields are preserved, which is genuine behavioral disclosure, but nothing is said about permissions, validation failures, side effects, or whether the whole `data` blob is replaced when supplied.
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?
One short sentence, front-loaded with the verb and resource, followed immediately by the one calling constraint that matters. There is no filler, and the colon structure separates action from instruction 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 mutation tool with a free-form nested object and no output schema, the definition covers the essentials but leaves gaps: valid field names for `data`, error behavior on unknown ids, and any company-scoping caveats beyond the company_id schema text. Note also that the description is in Italian while the rest of the tool surface is English, which is a minor consistency issue for an agent routing calls.
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 33%, so the description has to compensate. It does so for the most important gap: `data` is an unconstrained object with additionalProperties {}, and 'passa solo i campi da cambiare' explains that it is a sparse patch of changed fields rather than a full supplier representation. It still does not say which supplier fields are valid keys, which limits the value of the clarification.
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 plus resource ('Modifica un fornitore'), which maps unambiguously onto update_supplier and is distinguishable from delete_supplier, get_supplier and list_suppliers by verb alone. It stops short of explicitly contrasting with those siblings, but the update semantics are unmistakable.
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?
'passa solo i campi da cambiare' gives a real calling convention (partial patch, not full replace), which is the main way a caller could misuse this tool. Beyond that there is no guidance on prerequisites, no mention of when to prefer create_supplier versus update, and no statement about what happens when the id does not exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.