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

Annotations only declare readOnlyHint=false, idempotentHint=false and destructiveHint=false; the description goes well beyond them by disclosing the two-step confirmation flow, the 15-minute validity window of the tchin.tech confirmation URL, PIN-based user confirmation, and that fees are deducted from the requested amount. It does not say what happens on expiry or failure, which is the main remaining gap.

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 is front-loaded in the first two clauses, then prerequisite, then non-execution warning, then next step. Every sentence carries operational information; nothing is repeated from the title or schema.

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 mutating money-movement tool with no output schema, the description covers what is returned (a tchin.tech verification URL), who confirms (the user, with a Tchin PIN), the time limit, the fee treatment, and the required next call. An agent has enough to invoke it correctly without additional context.

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 80%, so the schema already documents most fields; the description adds real meaning by clarifying that 'frais pris dans le montant' means the montant is gross of fees, and that reseau must come from reseaux_retrait. It does not resolve the ambiguity between 'pays' and 'depuis', whose schema descriptions are identical, and telephone remains undocumented in both places.

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+resource pair: withdraws money from a country balance to a Mobile Money number, with fees taken from the amount. It also scopes the audience (Tchin merchant or individual, login required on first use), which lets an agent separate it from siblings like envoyer_argent, deplacer_argent or tchin_mobile_money.

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?

Explicitly names the prerequisite (call reseaux_retrait first to learn networks and their fees) and the follow-up (call etat_demande). It also states the crucial when-not-to-expect-execution condition: the call does not move money immediately, it prepares a request the user must confirm with their Tchin PIN.

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