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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context: the exact calculation rules, PASS reference years, and the express limitation. It doesn't contradict annotations and enriches understanding of how the tool behaves mathematically.

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 dense paragraph but well-structured: purpose, salarié formula, TNS/BNC formula, and limitations, with legal sources. It front-loads the core purpose and packs useful data without redundancy. It could be split into bullet points for readability, but it's appropriately sized for 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 no output schema, the description covers the essential calculation rules, PASS values, legal references, and exclusions. It doesn't explicitly state the return value (the ceiling amount), but that is implied. Given the complexity, it is sufficiently complete for correct invocation, though a note on edge cases (e.g., zero income) would make it fully complete.

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%, but the description goes beyond by explaining the meaning of tns (true/false) and how it affects the formula, including the 15% tranche between 1 and 8 PASS. It also gives concrete PASS values and the salary/TNS distinction, which helps the agent correctly map inputs to the intended regime.

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 clearly states the tool computes the annual PER deduction ceiling, with explicit formulas for salarié and TNS/BNC regimes. It distinguishes itself from siblings like fiscal_per_gain by specifying it handles the annual ceiling and is the 'express' version excluding reliquats and mutualisation, making its purpose 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 context: it explains it's for a single income, without reliquats or spousal mutualisation, implicitly telling the agent when NOT to use it. However, it doesn't name alternative tools (e.g., fiscal_per_gain for gains), so it lacks explicit routing to siblings, though the exclusion criteria are clear.

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