connect_site

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

No annotations are supplied, so the description carries the full burden, and it does substantial work: it declares a state-changing/control-scope operation, mandates user confirmation, and explains that behavior forks by vendor class — serial-number vendors return connected site ids, OAuth vendors return an authorize_url the user must open. It also discloses latency ("appears in list_sites within a minute"), though it does not address error modes or whether re-connecting an already-linked site is idempotent.

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?

Front-loads the highest-stakes information (account change + confirm first) before any vendor detail, and every following sentence adds distinct content rather than restating the schema. The all-caps opening is slightly shouty and the vendor-requirement clause is dense, but no sentence is wasted.

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 5-parameter mutation tool with zero annotations, the description supplies the safety signal, the per-vendor credential matrix, and the two-branch return contract; the presence of an output schema means it need not detail response shapes further. The only real gap is the undocumented region parameter and the absence of any failure-mode guidance.

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, and it does for the identifiers: it maps sn as the default credential, sn + nmi for Sungrow and FoxESS, and system_id for Sigenergy. It leaves region (default "AU") entirely unexplained, so one of five parameters remains undocumented in both schema and description.

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 ("Link the user's system to their Aivy account") plus a scope marker ("CHANGES THE ACCOUNT (control scope)") that immediately separates it from read siblings like list_sites and get_site. It also names the inverse operation's counterpart implicitly by telling the agent the site will appear in list_sites afterward, so the agent can place it in the lifecycle without opening any schema.

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?

Gives an explicit precondition ("Confirm with the user before calling") and an explicit exclusion ("Demo sites need no connecting"), which covers the main when-not case. It lacks direct routing to siblings such as list_vendors for discovering valid vendor strings or disconnect_site for undoing, but the context needed to decide whether to call it is clear.

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