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

Annotations already declare readOnly/openWorld=false, so the safety profile is covered. The description adds real context beyond that: it requires an authenticated session, and notes a login is prompted the first time, plus it discloses the 1 000 Tchin = 10 F exchange rate and the scratch-card concept. It doesn't cover failure modes or output format, but that is modest against annotation coverage.

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?

Two sentences, front-loaded with the audience/auth condition, then the payload contents. Dense but every clause contributes a distinct data point or constraint; no filler.

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 output schema, the description carries the burden of describing the return payload, and it does so by enumerating the four items returned. The only gap is the shape/format of those values (units, structure), which an agent can reasonably infer.

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 there is nothing for the description to disambiguate. Baseline for a parameterless tool is 4.

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 resource (the account's Tchin cashback) and enumerates exactly what is reported: Tchin earned, their F CFA value, pending scratch cards, and the conversion minimum. It is distinguishable from the sibling convertir_cashback (which acts) because this one reads. It stops short of naming siblings explicitly, which keeps it at 4.

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 by 'Pour l'utilisateur connecté à son compte Tchin' – it's the self-scoped read of one's own cashback. There is no explicit when-to-use versus alternatives, and no pointer to convertir_cashback for the conversion action mentioned at the end, so routing is left to inference.

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