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

No annotations are supplied, so the description carries the full burden. It does add genuine behavioral value by disclosing data-provenance behavior: amounts not re-verified against a promotional source are flagged ('Les montants non relus sur une source promotionnelle sont signalés'). It does not state that the operation is read-only, nor anything about result ordering, volume limits, or how the flag is surfaced in the response.

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 compact sentences with no filler, and the core resource definition is front-loaded before the data-quality caveat. Slightly dense phrasing in French with the purpose clause embedded mid-sentence, but nothing that could be cut without losing meaning.

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-optional-parameter read tool with no output schema, this covers the essentials: what is returned, the granularity, the history toggle's purpose, and a caveat about data verification. The remaining gap is that it never says the tool is non-mutating or describes the shape of the returned records, but that is modest given the tool's simplicity.

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 description coverage is 100%, so the baseline is 3; the description lifts it slightly by explaining the purpose of the history dimension ('pour juger si une offre actuelle est élevée'), which gives the include_history flag a rationale beyond the schema's mechanical 'true pour toutes les observations'. It still adds nothing about slug format for 'bank' beyond what the schema states.

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 names a specific resource (welcome bonuses / primes de bienvenue) and its grouping granularity ('par banque et offre'), plus a secondary capability (history for judging whether a current offer is high). It is clearly distinct from fee-oriented siblings like get_fees_barometer or get_bank_fees, though the verb is only implied by the tool name rather than stated.

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 the phrase 'avec l'historique pour juger si une offre actuelle est élevée', which tells the agent the history exists for comparison purposes, and the schema notes include_history defaults to false. However, there is no explicit statement of when to call this versus sibling tools such as compare_banks or get_evidence, and no exclusion criteria.

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