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

Beyond the read-only annotations, the description discloses non-obvious domain behavior: each RGDD block carries its OWN allocation key rather than one key for the whole copropriété, water/heating lines go by meter reading and the rest by lot thousandths, and the tool returns line-by-line output plus consistency checks and a balance (important since there is no output schema). Some failure semantics (missing quote_part blocks the statement, total_immeuble triggers refusal) live mainly in the schema rather than the prose.

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 trigger condition is front-loaded in the first clause and the sibling exclusion is placed last, which is good ordering. The allocation-rule sentence is dense but earns its place; the text is at the upper bound of length for a description of this complexity.

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 9-parameter, deeply nested tool with no output schema, the description supplies the mental model (per-block keys, two columns, meter vs thousandths), states what is returned, and routes to the sibling. Everything an agent needs to decide and call correctly is present across description and schema together.

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% with rich per-field descriptions, so the baseline is 3; the description still adds real meaning by explaining the two-column model (à répartir vs dont locatif) and the per-block key concept that governs how `blocs` and `quote_parts` must be populated. It does not add anything for the date/prorata or provisions fields, which the schema already handles.

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 opens with a precise trigger and verb ('établir le décompte de charges d'UN locataire' from a syndic's RGDD), so the resource and scope are unambiguous. It explicitly contrasts itself with the sibling regularisation_charges, so an agent can pick between the two without opening either 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?

States the exact when ('QUAND le syndic a envoyé son RGDD') and the when-not ('À utiliser à la place de regularisation_charges dès que les charges viennent d'un décompte de syndic : l'autre outil répartit des charges forfaitaires'). Both the trigger condition and the alternative are named, leaving nothing to inference.

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