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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral context beyond them: it defines data_confidence levels (high = official text, medium = translation or recent amendment), flags estimated_items, sources, warnings, and a not-legal-advice disclaimer. That disclosure of confidence and caveats is exactly the extra value the description should carry.

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?

Front-loaded with the core computation and legal basis, then the example, then the response shape — a sensible order with no filler sentences. It is dense, with heavy nested parentheticals, but each clause carries substantive information rather than restating the name.

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?

Given an output schema exists, the response enumeration is partly redundant, but the description still supplies what the schema cannot: which legal articles drive the numbers and what data_confidence means. Nothing critical for correct invocation is missing for a six-parameter, two-jurisdiction calculation tool.

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%, so the schema already documents all six parameters and the AE/SA enum. The description still adds value with a fully worked parameter example ('AE', '2024-01-15', '2026-10-31', 20, 6000) that shows realistic values and the interaction between taken_days and basic_monthly_wage.

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 and three concrete computations: accrued leave at a date, balance after days taken, and encashment value at the legal basis wage. It is clearly distinct from siblings like sick_leave_pay or end_of_service by jurisdiction-specific annual-leave articles (UAE Art. 29, Saudi Art. 109), though it never names a sibling 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: the AE/SA legal citations and the worked example make it obvious this is for annual-leave accrual in those two jurisdictions, but there is no explicit 'use this when…' or 'for sick leave / gratuity use X instead' routing. An agent must infer the boundary from the sibling names alone.

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