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

Annotations already mark this as non-read-only, idempotent, and destructive. The description adds behavioral context beyond these: it highlights that binding creates DNS records the user must create, and that it cannot modify ports/routes directly, which are limitations. It also mentions a recommended pre-read skill, which is a usage behavior. This adds value without contradicting the annotations.

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 description is well-structured, starting with the core purpose, then exclusions, then side-effects and a reading recommendation. Every sentence adds necessary information—there is no filler. It is slightly longer than minimal but the complexity of the tool justifies it.

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?

Given the tool's complexity (11 parameters, 2 required, output schema), the description covers what can be updated, what cannot, alternatives, side-effects, and a prerequisite read. The presence of an output schema means return values don't need elaboration. It is a complete, self-sufficient description.

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?

The input schema already provides 100% parameter descriptions (e.g., tags: 'Add or update tags without replacing the full set. Submit an empty list to clear all tags.'). The description groups parameters into meaningful categories (metadata, spec flags, bindings) and introduces the DNS side-effect, but does not provide syntax beyond the schema. Baseline for full schema coverage is 3; the grouping and side-effect note add a little, but not enough to exceed.

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 clearly states the tool updates metadata (description, tags), spec flags (acceptAllHosts, acceptAllSubdomains), and GVC/workload bindings. It explicitly differentiates from siblings by listing what it cannot do and directing to add_domain_route, update_domain_route, remove_domain_route, add_domain_port, remove_domain_port, set_domain_tls, and clear_domain_tls for routes, ports, and TLS. This gives a precise verb+resource distinction.

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 provides explicit when-to-use vs. alternatives: 'CANNOT change ports or routes directly' followed by the exact sibling tools for routes, ports, and TLS. It also advises re-reading status.dnsConfig after binding gvcLink/workloadLink to create required DNS records, and recommends reading get_cpln_skill('domain') before first use. This is clear context with exclusions and prerequisites.

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