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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description adds the non-obvious fact that the tool 'opens nothing by itself' and that the return value is a step-by-step procedure. That is real value beyond the annotations. It does not disclose whether the Cloud Browser must already be logged into JazzHR, which is the main remaining operational unknown.

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 key correction (guide, not action) and the follow-up tooling are front-loaded in the first sentence. The trailing sentence about JazzHR's REST API is context rather than instruction and slightly bloats the definition, but each sentence serves a purpose.

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 zero-parameter guide tool with no output schema, it covers what is returned and what to do next. It omits prerequisites that matter for the subsequent browser steps, such as whether the JazzHR Cloud Browser session must be authenticated and whether the user must supply candidate identity during the conversation.

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?

There are zero parameters, so the schema has nothing to document and the baseline applies. The description implicitly accounts for this by framing the output as generic step-by-step instructions rather than an execution that would need candidate or note inputs, though it never explicitly says no inputs are required.

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 resource (JazzHR candidate note) and, crucially, corrects the misleading verb in the name: it does not add a note but 'Returns how to do it in JazzHR step by step.' An agent can tell this is a guidance/how-to tool rather than a mutation, which distinguishes it from the actual JazzHR mutation siblings.

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 an explicit two-step workflow: call this to get the screens/buttons/fields, then execute with the cotlet_browser_* tools in the user's JazzHR Cloud Browser. It also explains why the browser route exists (REST API needs a key from Settings > Integrations, no official MCP server). It doesn't say when to skip this in favor of a direct JazzHR sibling tool, but the routing it does provide is actionable.

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