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

Annotations already declare readOnly/openWorld=false/destructive=false, so safety is covered; the description adds the key behavior beyond that: it returns an address rather than executing anything, and authentication may be triggered on first use. It stops short of saying whether the URL is single-use or how long it stays valid.

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 auth prerequisite are front-loaded, followed by a compact page catalogue. The enumeration is long but every entry does disambiguation work; the only mild redundancy is that the introductory clause and the page list both restate the in-app action set.

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?

No output schema exists, yet the description explicitly states the return is a page address, and the prerequisites and page inventory are covered. What is missing is only marginal (URL lifetime, what happens for a non-authenticated user), so it is complete enough to invoke correctly.

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 description coverage is 0%, so the description carries the full burden — and it does, glossing all 13 enum values with what each page contains (e.g. 'api' holds applications and their secret key requiring the Tchin PIN, 'banque' includes coffres). This adds real meaning beyond the bare enum strings.

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?

States a specific verb and resource ('Rend l'adresse d'une page de Tchin') and scopes it to the logged-in user's in-app screens, so an agent knows this returns a deep link rather than performing an action. It does not name any sibling tool (mes_transactions, mon_compte, tchin_crypto…) to contrast against, which keeps it from a 5.

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?

'Pour l'utilisateur connecté… (connexion demandée la première fois)' gives an auth prerequisite, and 'pour ce qui se fait sur l'écran de Tchin' frames the context. However there is no explicit when-to-use-this-vs-sibling guidance despite ~40 siblings that cover the same domains programmatically; the agent must infer that this is for handing a URL to a user rather than fetching data itself.

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