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

Annotations already declare readOnlyHint=true, destructiveHint=false and closed-world, so safety is covered; the description adds meaningful extras: an authentication prompt on first use, the default and maximum time window, and the fact that failed and pending operations are included alongside successful ones. It stops short of describing result structure or volume/pagination behavior for what could be a large aggregate.

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 sentence plus a scope clause, front-loaded with who the caller is before the enumeration of what is returned. Every clause carries information; the parenthetical login note is slightly buried mid-sentence.

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 usefully enumerates the dimensions of the report (entries/exits by genre, month, country, fees, failed/pending), which is what an agent needs to judge relevance. Authentication requirement and time bounds are stated; the shape of the returned object is not, but that is largely covered by the dimension enumeration.

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 the baseline is 3; the description earns a bump by adding the default window (30 days) and hard cap (one year), which materially constrain how du/au can be used. The mode enum values are already documented in the schema and are not repeated.

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: aggregates ALL successful operations for the connected Tchin user (merchant or individual) over a period, broken down by genre, month, country, plus fees and failed/pending operations. This is clearly an aggregation/report tool, distinct from list-style siblings like mes_transactions or detail_transaction, though no sibling is named explicitly.

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?

Gives useful context (connected-user scope, first-time login prompt) and period constraints (30 days default, one year max), which implies when it applies. However, it never says when to prefer this over rapport_ventes, mes_transactions or releve_pdf, leaving alternative selection to inference.

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