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

Annotations already establish readOnly/non-destructive/closed-world, so the description's added value is the behavior around the link: single-use, 2-minute expiry, opens in the user's already-authenticated browser, and a single reused tab. Those are exactly the traits an agent cannot infer from annotations. It stops short of saying what the call returns (presumably the URL) or what happens on expiry or invalid paths.

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?

Purpose and the 2-minute expiry are front-loaded in the first sentence, and the long path enumeration earns its space as reference material for a free-form string parameter. Structure suffers slightly: the path catalogue is a single comma-chained run rather than a scannable list, and the parenthetical asides make it dense.

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 one-parameter tool with annotations covering the safety profile, the description covers the important unknowns: link lifetime, single use, authentication context, tab reuse, and valid path shapes. However, with no output schema, the agent is never told what the call returns or how to surface the link, which is a meaningful omission for a tool whose whole output is a URL.

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?

Schema coverage is 0% — the single 'path' parameter has no description at all — so the description carries the full burden and largely meets it, enumerating concrete path templates (/dashboard, /editor/<pageId>, /site-projects/<id>/preview, /dashboard/presentations/<id>/present, etc.) and tying resource names to describe_resources. Gaps remain: the list ends in an ellipsis, and there is no statement about leading slash, query strings, or behavior on an unrecognized path.

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 verb and resource: it produces a single-use (2 min) link that opens a named Outil page inside the user's own browser session. That is far more precise than the title 'Open in outil'. It does not explicitly contrast itself with near-siblings such as show_preview or preview_components, though it references preview_components only as a path target.

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?

Usage is implied rather than stated: 'pour qu'il voie ce que tu fais' suggests the user should visually follow along, and the note about reusing a single Outil tab is a useful operational hint. There is no explicit when-to-use/when-not, and no alternative tool is named for cases where the agent should not open a browser tab (e.g., headless reads via get_page).

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