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

Annotations already declare destructiveHint=true, idempotentHint=false and a write operation, so the bar is lower. The description still adds real context: every change is historized (visible via ficiel_get_cash), the write scope is required, and effective_date schedules the new amount from Paris midnight rather than immediately. It does not describe the response or confirm whether erasing with null removes past history.

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?

A single dense block with the core rule (amount, range, null) front-loaded before scheduling, history and scope details. Every clause carries information, though the phrasing is compressed enough that the one-year cap and midnight semantics take a careful read.

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 two-parameter write tool with rich annotations and no output schema, the description covers units, valid range, null-erase, scheduling semantics, history and required scope. The only gap is that it says nothing about the call's outcome or confirmation, which an agent might want for a destructive, non-idempotent write.

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 100%, so baseline would be 3, but the description adds constraints not present in the schema: the effective_date is capped at one year out and takes effect at midnight Paris time on that day. It also restates the integer range and null semantics, which is redundant with the schema's min/max/anyOf.

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 ('Règle le montant de votre offre... c'est le panier qui sert à estimer le cash dormant'), plus units and the null-to-erase behavior. The stated purpose (the reference basket used to estimate dormant cash) distinguishes it from the similarly named sibling ficiel_set_lead_deal_amount without needing the schema.

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?

It gives context on what the value feeds (cash-dormant estimation) and points to ficiel_get_cash for history and shared access gates, but it never says when to set this versus the per-lead sibling ficiel_set_lead_deal_amount or any other alternative. Usage is implied rather than routed.

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