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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's real value is disclosing that nothing is opened and that the return is procedural guidance rather than data — an important non-obvious trait. It does not describe the shape or length of the returned steps, nor any auth/connection requirements, keeping it below a 5.

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 purpose and hand-off are front-loaded well, but the second half wanders into Tidio's official API plan tiers and a dated parenthetical ('checked 17 Oct 2026') that is tangential to invoking this tool. That detail justifies the routing decision but is longer than needed and dilutes the core instruction.

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, no-output-schema guidance tool, the description covers what it returns (steps with screens, buttons, fields), what it does not do (open anything), and the follow-up path (cotlet_browser_* tools). Only the exact form of the returned steps and any setup prerequisites remain unstated.

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 implicitly confirms no inputs are needed (no account ID, conversation ID, or query). Nothing further is required of the description here.

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 the resource (Tidio conversation history) and immediately corrects the misleading name by clarifying the tool returns step-by-step instructions (screens, buttons, fields) rather than the history itself, and that 'it opens nothing by itself.' It also distinguishes this from Tidio's official REST API path. The verb/resource pairing is clear, though the tension between the name 'read conversation history' and the actual guidance-only behavior costs a point.

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?

Explicit routing: after getting the steps, the agent should 'do it with the cotlet_browser_* tools in the user's Tidio Cloud Browser,' and the API caveats (Plus/Premium only, official MCP servers can't work the inbox) explain why this route is needed. It gives clear context for when to use this, but stops short of naming explicit when-not conditions or prerequisites such as a connected Tidio account.

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