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

With no annotations, the description carries the full burden of behavioral disclosure. It adds beneficial context: the definition of 'touched', the Monday-to-Sunday week boundary, and per-currency breakdown. However, it does not explicitly state that the operation is read-only, idempotent, or side-effect free, and it gives no indication of how missing data or multiple currencies are handled. These traits are largely inferable from the word 'summary', but the description itself does not disclose them.

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?

Three sentences with no filler: the first gives the high-level output, the second defines the week, and the third defines inclusion. Each sentence earns its place, and the most important concept ('touched') is defined clearly. Structure is efficient and front-loaded.

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 tool with only two optional parameters and no output schema, the description explains what the summary contains (hours, value, per worker, per currency) and how the window is determined. The absence of an output schema is partially mitigated by the enumeration of output categories. Minor gaps remain (e.g., behavior with no entries, multi-currency presentation), but given its low complexity, the definition is largely 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%, so the baseline is 3, but the description enriches the parameters by explaining how 'date' selects the window and how 'span' maps to a calendar week. Crucially, it introduces the 'touched' rule, which defines which job cards are included based on dated entries. This adds meaning beyond the schema's plain descriptions of date and span.

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 relationship: summarizing hours and value for a day or week, covering job cards touched, hours per worker, and labor/material/total value per currency. This clearly distinguishes it from siblings like job_card_list (raw entries) or job_card_log_labor (recording entries). The title 'Summarize a day or a week' reinforces the exact scope without ambiguity.

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 on the time window ('A week runs Monday to Sunday') and the inclusion rule ('Touched means a labor or material entry dated inside the window'), which helps an agent decide between day and week spans. However, it offers no explicit guidance on when to choose this tool over siblings like job_card_get or job_card_list, nor does it mention exclusions or alternatives. The usage context is useful but not prescriptive.

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