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

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses key behavioral details: immutability of history, exclusive end_date with default, bounded cursor pagination, and handling of unknown history. This is exactly the kind of context an agent needs to interpret results correctly.

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 sentences with zero fluff: the first states the purpose and the second packs critical behavioral nuances. Highly effective 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?

With no output schema, the description offers an overview of the returned data (daily completions/reopens, status, point coverage) and addresses edge cases (unknown history). The interaction between days and end_date could be more explicit, but overall the tool is well-specified for its purpose.

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 0%, so the description must compensate. It explains end_date (exclusive, default today UTC), implies label is the cohort selector, and references bounded pagination for limit/cursor. The 'days' parameter is only indirectly implied via 'daily observations' and 'UTC window start'; a direct explanation would push this to 5.

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 ('Report') and names the resource clearly: a fixed cohort holding one exact label at the UTC window start, with observed daily completions/reopens and status/point coverage. This distinctly separates it from siblings like get_ticket_label_history or get_ticket_burndown.

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 implies when to use it (to get a cohort snapshot for a specific label over a time window) and provides caveats like 'Today's labels never rewrite history' and 'unknown history is disclosed,' which help an agent judge suitability. It doesn't explicitly name alternatives, but the specificity narrows the decision space.

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