get_week_history

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

No annotations are provided, so the description carries the burden. It describes the return content accurately (snapshots keyed by ISO week, newest last) and the ordering behavior. However, it doesn't disclose what 'closed-week' means operationally, whether the current in-progress week is excluded, or the format of the metrics object. The return shape is partially explained but behavioral edge cases are unaddressed.

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 description is compact (a few lines) and front-loaded with the core purpose. It includes a brief 'Returns:' section that clarifies the output structure. It's efficient without excess, though the repeated mention of 'week history keyed by ISO week' is slightly redundant at the end.

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?

With 0 params, no annotations, but an output schema present, the description explains the return shape (keyed by ISO week, newest last, includes metrics + executive note). The output schema presumably carries detailed return structure, so the description complements it well. It could note the relationship to close_week (a sibling) but is generally adequate.

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?

The tool has 0 parameters, and there is no input schema to compensate for. With no parameters to document, the description doesn't need param details. The 0-param case is inherently fine; the description explains what data comes back instead, which is appropriate. Baseline 4 for 0 params.

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 clearly states it retrieves the tech dashboard's closed-week snapshots with specific detail (metrics + executive note), newest last, plus the current ISO week key. It has a specific verb (get) and resource (closed-week snapshots). Among siblings like get_today_events, get_week_events, and get_morning_briefing, this is reasonably distinguishable, though it shares a general 'history' theme with get_person_history.

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 explains WHAT it returns (snapshots, metrics, executive note, ISO week key) but offers no guidance on WHEN to use it versus alternatives like get_week_events or close_week. It doesn't clarify that it only shows closed weeks (not the current week), nor does it distinguish from get_event_details or weekly briefing tools. No exclusions or alternatives are mentioned.

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