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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), the description discloses authorization requirements, the restart prerequisite, the per-port/per-instance quotas, and the fact that no firewall rule is involved. What it does not say is whether an existing link can be adjusted without deleting it, or what happens if the port already has a link; idempotency is left to the annotation alone.

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 purpose is front-loaded in the first clause, before the access modes and constraints, and every sentence conveys a rule an agent needs. It is a dense single paragraph, though, and the access-mode explanation sits between the core action and the hard limits, which slightly buries the port exclusions and quotas.

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 6-parameter creation tool with no output schema, nothing an agent needs in order to call it correctly is missing: what it exposes, to whom, the limits, the permissions, and the restart caveat are all present. Return behavior is implied clearly enough by the phrase "at its own HTTPS link."

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 real meaning by unpacking the access enum: "workspace" means signed-in members opening from the Runcrate dashboard, "public" means anyone with the URL, and "ips" restricts to the addresses in sources. The sources parameter is thereby tied to a specific access mode, which sharpens its use.

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?

"Serve one TCP port of a running instance at its own HTTPS link" gives a specific verb (serve/expose), a precise resource (one TCP port of an existing instance), and the output (an HTTPS link). It also distinguishes itself from add_firewall_rule by stating "Needs no firewall rule, and from delete_instance_link/list_instance_links by being a creation operation.

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?

The description states the target case (a web app or API listening over plain HTTP on 0.0.0.0), explicit exclusions (not port 22 or Runcrate's own ports), capacity rules (one link per port, up to 10 per instance), authorization (owners, admins, and the launcher), and a prerequisite (an instance predating the firewall must be restarted first). It also explains that no firewall rule is needed, which prevents a wrong tool choice.

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