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

Annotations already declare the safety profile (readOnly=false, openWorld=true, destructive=false), and the description adds substantial context beyond them: the repo must contain finished static HTML with no build step, private-repo tokens must never be requested in chat, and auto_publish bypasses approval so it needs explicit consent. This is exactly the behavioral detail the structured fields cannot convey.

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 core concept and the four actions are front-loaded before the operational caveats. It is a long paragraph, but for a four-action tool with safety constraints most sentences earn their place; some of the parameter restatement is redundant with the schema.

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?

With no output schema, the description carries the burden and does so: it explains what 'get' returns (settings plus webhook URL, secret, and last-run result), the full lifecycle of the other actions, and the hand-off to deploy_publish. For a 7-parameter, four-action tool this is complete enough to invoke correctly.

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 100%, so the baseline is 3, but the description adds value beyond the schema by giving concrete formats and defaults: repo as 'besitzer/name', subdir example 'dist' (empty = repo root), branch default 'main', and the semantics of auto_publish. It does not fully re-explain every parameter, which is fine since the schema handles them.

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 ('Git-Anbindung einer Website verwalten') and enumerates the four actions (get/set/run/remove) with what each does. It explicitly positions itself relative to siblings deploy_preview and deploy_publish, so an agent can distinguish it without opening the 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?

It gives explicit when-to-use per action, names the alternative workflow (deploy_preview then deploy_publish with the deploy_id), and states a hard condition for auto_publish=true ('nur ... wenn der Nutzer das ausdrücklich so will'). Post-set follow-up (webhook_help, handing over URL and secret) is also prescribed.

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