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

With only destructiveHint=true in annotations, the description carries real weight: it discloses the restart side effect, the upsert behavior, the name/value size limits, the underlying API call, and the return shape. It stops short of saying whether variables omitted from the array are left intact or removed, which is the key unknown for a bulk PUT.

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 dense paragraph that front-loads the mutation warning, then side effects, limits, endpoint and return value in priority order. Only the repeated size limits are wasted words since the schema already covers them.

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 with no output schema, the definition covers safety signal, side effects, constraints and return shape ('Returns { variables }'). The main omission is whether the operation is additive or a full replacement of the app's variable set.

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 100%, so both parameters are already documented. The length limits restated in the description (≤64 name, ≤8192 value) duplicate the schema's own descriptions rather than adding semantics; baseline 3 applies.

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 opens with a specific verb and resource: 'MUTATES Scalingo infrastructure — creates or updates environment variables in bulk.' That scope cleanly separates it from the read-only sibling scalingo_list_variables without either schema being opened.

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?

Upsert semantics ('created if new or updated if it exists') imply when this is the right call, and the bulk framing implies it replaces per-variable single writes. However, it never names scalingo_list_variables as the read path or states any exclusion, so the agent must infer the boundary.

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