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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered structurally. The description adds the substantive behavioral fact that comparison is performed 'sur les mêmes chiffres' across a fixed metric set, which tells the agent what it will get back. It does not cover what happens with unrecognized SCPI names or how few metrics are returned when data is missing.

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 front-loaded sentence with no filler; the comparison scope and metric list both earn their place. Slightly dense with the parenthetical metric enumeration, but nothing is redundant.

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?

Simple read-only tool with one fully documented parameter and no output schema, so the description carries the return-content burden — which it does by enumerating the compared metrics. Only minor gaps remain around error handling and accepted input format for SCPI identifiers.

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% and the single 'scpis' parameter is documented in the schema, including minItems/maxItems. The description's '2 à 4' merely restates those constraints rather than adding format guidance (e.g. whether names must be exact, accent- or case-sensitive).

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 uses a specific verb ('Compare') with a clear resource ('SCPI') and states the cardinality (2 to 4) plus the exact metrics compared (prix, taux de distribution, taux d'occupation, capitalisation, frais, valeur de reconstitution). It implicitly distinguishes itself from single-entity siblings like fiche_scpi, but never names an alternative 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?

Usage is only implied: an agent can infer this is the tool for multi-SCPI side-by-side comparison, and the 2–4 bound is stated. There is no explicit guidance on when to use fiche_scpi or rechercher_scpi instead, nor any prerequisite such as needing valid SCPI names or identifiers.

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