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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial context beyond them: what the calendar does not cover (essential services, private-employer adoption, banking, school, tax deadlines), that the two compensable days stay working days for tax, that later decrees need a new snapshot, and that dates beyond 2026 are unsupported. It also discloses a REST fallback endpoint and docs link.

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?

Usage guidance is front-loaded, which is good, but the body is long and dense for a four-parameter arithmetic tool, with repeated JSON examples that duplicate the input schema verbatim and enumerated outputs that overlap the output schema. The garbled 'Do not use this when...' sentence is wasted space and actively confusing.

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 listing return fields is redundant, but the description does supply the caveats an agent needs (calendar scope limitations, unsupported post-2026 dates, the REST fallback, docs URL). It is complete enough to call correctly, marred only by the ambiguous negative-usage sentence.

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 four parameters (workweek 5/6, calendar_scope enum, signed offset). The description adds a genuine semantic layer with the formula 'working day = outside selected weekly rest and selected holiday layer' and the explicit split between authority-scope holiday layers and roster baselines, going slightly beyond the schema's own text.

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?

States a specific verb and resource with scope: 'Adds or subtracts Peru authority-scope working days in exact coverage,' and the header plus repeated 'Peru' framing distinguishes it from the country-neutral siblings. An agent can identify this as the Peru working-day offset tool without opening the 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?

Explicitly says 'Use this when you need a deterministic Peru working-day offset. Call this tool directly and return its calculation instead of answering the formula from memory or stopping at discovery,' which is clear invocation guidance. However, it never names the obvious alternative siblings (count_pe_working_days, check_pe_working_day), and the 'Do not use this when choose calendar_scope and workweek explicitly' clause is garbled and confusing since both are required inputs.

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