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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety. The description adds behavioral context: it is stateless, performs a complete recalculation of multiple taxes, and accounts for the CDHR cap, explaining that the marginal gain can be ~20% rather than the TMI. This goes beyond the annotations and helps the agent understand the computation's nature.

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 description is a single paragraph that packs the core purpose, a formula, a critical warning, a stateless note, and legal references. Every sentence adds value, though the legal citations could be considered optional. It's front-loaded with the main purpose and remains concise given the 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 calculation tool with six parameters and no output schema, the description covers the essential context: what is computed, how it's computed (full recalculation), the key caveat about CDHR, and legal sources. It implies the output is a monetary gain, which is adequate for a single-value tool. It could mention the exact output format but that's a minor omission.

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 all parameters are already documented in the schema. The description adds minimal extra meaning about parameters: it mentions the RFR is reduced and hints at CDHR relevance, but it doesn't significantly deepen the understanding of each parameter beyond what the schema provides. Baseline 3 is appropriate.

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 explicitly states the tool computes the total tax gain from a deductible PER payment as Δ(IR + CEHR + CDHR), with a clear verb ('Gain') and resource ('versement PER'). It distinguishes itself from siblings by emphasizing a full recalculation rather than a simple marginal-rate multiplication, and it names the taxes involved, making its scope unambiguous.

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?

The description provides clear guidance on when to use the tool: whenever the total tax saving of a PER contribution is needed, and it explicitly warns against using marginal tax rate times contribution ('jamais TMI × versement'), implicitly steering away from simpler tools like fiscal_tmi. It doesn't name sibling tools directly but the caution effectively differentiates it. A minor gap is not explicitly listing alternatives, but the guidance is sufficient.

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