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

With no annotations, the description carries the full burden and does well: it discloses that the range is resolved on the shop's calendar, that a historical anchor can be supplied, and crucially that the operation executes under the caller's own permissions — a real authorization constraint an agent cannot infer. It stops short of stating that the run is non-mutating, which would close the loop for a no-annotation tool.

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?

One front-loaded sentence with the core behavior first and the date-resolution nuance second; no filler. The trailing 'Returns the exact input used and the operation's result' is somewhat redundant given an output schema exists, but it is brief.

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 no prose, and the description still covers the non-obvious parts: calendar-based range resolution, the as_of override, and permission scoping. The one real gap is how an agent obtains and validates report_id before calling.

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?

Coverage is 50% (only as_of is described in the schema). The description reinforces as_of's meaning ('or around as_of') and explains the default resolution path, which is genuinely additive, but report_id is undocumented in both places beyond its UUID format — the text only implies it names a previously saved report.

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?

'Run a saved report' pairs a specific verb with a specific resource, and the 'saved' qualifier separates it from the canned report siblings (reports_revenue, reports_today, reports_week) and from reports_save / reports_listSaved. It never names those siblings explicitly, so the differentiation is implicit rather than stated.

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?

'Run ... now' implies immediate execution of an existing saved definition, which is a usable signal. But there is no explicit when-to-use/when-not, no pointer to reports_listSaved for obtaining a report_id, and no guidance on choosing this over the fixed reports_* report tools.

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