Создать или настроить расширение

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

Annotations (readOnly=false, destructive=false, idempotent=false) set the safety profile, and the description adds real beyond-schema behavior: omitted fields are preserved on edit, and passed arrays replace prior ones entirely — a non-obvious gotcha — plus the warning to retain operation IDs. It stops short of noting auth/permission needs.

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?

Three tight sentences, front-loaded with the create-vs-edit distinction and the most important behavioral caveat (array replacement). No filler; every clause carries information.

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 16-parameter, deeply nested tool with no output schema, the description covers the pivotal create/edit and array-replacement semantics but omits guidance on the large auth/webhook/connection configuration surface. Adequate for the key risks, incomplete overall.

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 only 19%, so the description must carry the load. It clarifies name/base_url for creation and the replace-whole semantics of operations/events arrays, but the vast majority of the 16 params (auth, headers, query, webhook, timeout, port, etc.) remain undocumented in both description and schema.

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+resource ('creates a connection' / 'configures an extension') and clearly separates its two modes via the presence of the 'extension' parameter. An agent can tell create-vs-edit apart from the sibling read/delete tools, though it does not name them explicitly.

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 concrete when-to-use guidance: no 'extension' => create (requires name and base_url); with 'extension' => edit. This is clear context, but it doesn't point to alternatives like extensions_get/extensions_list to discover an existing ID first.

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