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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false; the description reinforces rather than contradicts this by stressing the tool opens nothing and only returns instructions. It adds genuinely non-obvious context beyond the annotations: the output is a procedural walkthrough and the real mutation must be carried out by a separate family of browser tools. It omits what happens if no e-Boekhouden environment is connected or how the instructions are scoped to a specific mutation.

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 core information is front-loaded and compact, but the sentence contains filler ("from ChatGPT, Claude or any AI agent") and a cryptic trailing fragment ("e-Boekhouden's official API: Yes") whose meaning is never explained. The three ideas are run together in a single block rather than separated for scanability.

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, no output schema, and annotations already covering the safety profile, the description's main obligations are met: it says what comes back (a step-by-step guide) and what to do next (browser tools). It falls short on the zero-parameter puzzle and on prerequisites or failure modes, which matter for a tool whose real work happens downstream.

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 at 100% schema coverage, so there is nothing for the description to disambiguate and the baseline of 4 applies. One residual concern is that with no inputs at all, the description never explains how the returned guide is tailored to a particular mutation, leaving the agent to infer it from conversation context.

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 makes the actual behavior explicit: it returns step-by-step instructions (screens, buttons, fields) for booking a mutation rather than performing one, and states that it "opens nothing by itself." This resolves the ambiguity of the name and the potentially misleading word "mutation." It does not, however, distinguish itself from siblings like e_boekhouden_create_invoice or e_boekhouden_add_relation, which also touch bookkeeping records.

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 two-phase workflow: call this first, then execute with cotlet_browser_* tools in the user's Cloud Browser. That is useful sequencing guidance. But it never says when to prefer this over the direct-API siblings (create_invoice, add_relation), which is exactly the choice an agent faces, and offers no exclusions or prerequisites such as needing an e-Boekhouden account connected.

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