hcm_rest_get

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

Annotations already carry readOnlyHint=true; the description adds that access is allowlisted and that CE/generative-AI/internal paths will be blocked, which is useful operational context. It does not describe errors, pagination, or response shape, but those are not required for a simple read-only pass-through given the annotation.

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?

Two short sentences, no filler, and the core operation is stated first. The second sentence earns its place by giving a hard constraint.

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 generic pass-through tool with no output schema and an opaque allowlist, the description is too thin: it does not say when to prefer hcm_rest_get over the many dedicated getters, what the allowed path prefix is, or how responses are returned. An agent would need extra exploration to call it confidently.

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 schema documents 'path' with an example but leaves 'query' essentially undescribed; the description adds no parameter-level information. With only 50% schema description coverage, the missing query semantics are not compensated.

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 names the operation (GET) and target (HCM resources) and adds a concrete boundary via the blocklist for CE/generative-AI/internal paths. It does not enumerate the allowed resource set, but it is distinguishable from the custom getters like hcm_get_worker because it is explicitly generic.

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 phrase 'generic GET' and 'Blocked for...' imply this is a fallback raw REST read and gives an explicit when-not-to-use for certain path categories. It never mentions alternatives such as specialized getter tools or hcm_rest_mutate, so the routing decision is left largely to inference.

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