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

With no annotations, the description carries the burden and does disclose meaningful behavior: only approved hours, waiting/running time excluded, two-decimal hours, one row per person per day, and an 'Owner or office' permission requirement. However, 'check ready' is unexplained and it never states error behavior or whether the export is idempotent/non-mutating.

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?

Two dense sentences, front-loaded with the output shape and column semantics, with no filler. The telegraphic fragments ('check ready', 'Owner or office') are terse to the point of ambiguity but not verbose.

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 need not be explained, and the description usefully summarizes the CSV row content. Still missing for a 5-parameter export tool: what 'ready' means, how the pay period is resolved when only date is given, and behavior on empty/partial data.

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 60%: date, from, and offset are already documented in the schema, while shop_id and to are not. The description adds only that the target is 'one pay period', without explaining how date vs. from/to interact or what offset does beyond the schema text, so it does not compensate for the coverage gap.

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 uses a specific verb and resource ('export approved hours as CSV for a payroll provider') and specifies the row granularity and columns, which distinguishes it from payroll_hours and payroll_getPeriod. It never names a sibling explicitly, so differentiation relies on inference from the output format.

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?

'Approved hours for one pay period' and 'check ready' imply usage context (period must be approved/ready before exporting) but no explicit when-to-use or when-to-prefer-alternatives guidance is given. The agent must infer that payroll_hours is the non-export alternative.

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