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

Beyond the readOnly/non-destructive annotations, the description discloses the authentication requirement, the sort order (most recent first), the aggregate totals returned alongside the filtered rows (entrées, sorties, frais), the page size behavior, and that each row carries its originating canal. With no output schema present, this return-shape disclosure is exactly what the description needs to carry.

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?

The scope and ordering come first, followed by filters and then pagination/return shape, which is a sensible front-loading. It is a dense semicolon-chained paragraph and repeats enum values already documented in the schema (genre, canal, mode), so a few clauses do not add new information.

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 10-parameter, all-optional read tool with no output schema, the description covers scope, ordering, every meaningful filter, defaults, limits, and the returned totals and canal field. Remaining gaps are minor: the 'page' parameter is not described and there is no note on what an empty result looks like.

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 60%, and the description closes most of the gap: it explains genre meanings, that canal means payments from WooCommerce stores or WordPress buttons, that mode defaults to 'reel', and that pagination defaults to 25 with a 100 ceiling (a default the schema does not encode). Only 'page' is left unstated, and it is self-evident alongside limite.

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?

The description states a specific verb and resource: it returns the FULL transaction history of the connected Tchin account, ordered most-recent-first, and enumerates the record genres (paiements reçus, dépôts, retraits, envois, cashback, épargne, etc.). That enumeration implicitly separates it from narrow siblings such as mes_retraits, mes_ventes, or detail_transaction, but those alternatives are never named, so sibling differentiation is left to inference.

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 context is clear: it applies to the logged-in user's own account (merchant or individual) and requires a first-time connection. The filter dimensions are spelled out, which tells the agent how to narrow results. It never says when NOT to use it, e.g. that detail_transaction is the right tool for a single transaction or that bilan_compte covers aggregate balances, so exclusions are absent.

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