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

Annotations declare readOnly=true, destructive=false and idempotent=true, and the description explains why: 'opens nothing by itself', it only returns a procedure. It also discloses the required follow-up mechanism (cotlet_browser_* in the user's Cloud Browser) and the absence of a public API, which are behavioral facts the annotations do not carry.

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 critical non-obvious fact — that it opens nothing and only returns instructions — is front-loaded in the first sentence. It loses a point for a run-on construction, the doubled 'check in in', and a slightly expendable 'from ChatGPT, Claude or any AI agent' clause.

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 parameters and no output schema, the description carries the full burden of describing what comes back, and it does: step-by-step screens, buttons, and fields. It also tells the agent what to do next, so the workflow is closed end to end.

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 tool takes zero parameters, so the baseline is 4. The description adds nothing about inputs because there is nothing to add, though it does implicitly explain why no parameters exist (the tool emits a guide, not a scoped operation).

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 a specific verb and resource (submit a personal check-in) and immediately resolves the mismatch between the name and reality: the tool returns step-by-step instructions rather than performing the submission. That distinction is the single most important thing an agent needs to know, and it is stated explicitly in the first sentence.

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 a clear usage chain: call this to get screens/buttons/fields, then execute with the cotlet_browser_* tools in the Cloud Browser. What it lacks is disambiguation from adjacent siblings such as respond_to_check_in, generate_check_in_draft, or list_check_ins, so the agent must infer which check-in tool applies when.

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