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

Annotations already cover readOnly, idempotent, non-destructive, and non-open-world, but the description adds substantial behavioral context beyond them: Ministry of Interior precedence over secondary snapshots, lunar/amendable Eid dates, the Public Holidays Act rule that no substitute day is invented for weekend holidays, the computation formula, and a REST fallback with an explicit warning not to guess other paths. This is materially useful, slightly undermined by the garbled grammar.

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 text is bloated and corrupted: 'Nigeria Nigeria', '2026-2026', a self-contradictory 'Do not use this when this is...', plus a full output-field dump. It is loosely sectioned (Use/Do not/What it computes/Inputs/Outputs/Formula/Fallback/Docs) but key intent is buried behind repetition and duplication.

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?

An output schema exists so return values needn't be explained, yet the description still lists outputs. It covers scope boundaries, authority precedence, lunar caveats, the computation formula, a REST fallback URL, and docs link – enough for an agent to call it correctly. The main deficiency is the broken when-not guidance rather than missing factual content.

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% for the single date parameter, so the baseline is 3. The description repeats the input ('Inputs: date (date)') and supplies complete JSON argument examples, but adds no format or meaning beyond what the schema already states.

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 states a specific verb+resource (checks a date against a Nigeria 2026 federal working-day calendar) and later a formula, so the core function is recoverable. However, the opening is garbled ('Nigeria Nigeria 2026 nationwide federal public-holiday calendar over a Saturday-Sunday weekend result') and it never explicitly distinguishes itself from the sibling check_ng_working_day vs count_ng_working_days vs add_ng_working_days family.

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?

It does give one useful directive ('Call this tool directly and return its calculation instead of answering from memory'), which is real usage guidance. But the 'Do not use this when...' clause is malformed – it restates scope limitations (nationwide federal, not state/private/sector) rather than naming an actual condition or alternative tool, so the when-not guidance is only implied.

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