run_report

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

Annotations declare readOnly=false, idempotent=true, destructive=false, and the description adds real context beyond them: asynchronous/background execution and the fact that its default privacy filtering diverges from Gramps' own default. It does not say where the output file lands, but the async and default-behavior disclosures are substantive.

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 tight sentences, front-loaded with purpose, then the important default-behavior caveat, then the async execution note. Every sentence earns its place with no filler.

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 carries the burden of explaining return values and does so by describing both the file output and the task_id polling path. The 'usually' hedge leaves mild ambiguity about which outcome to expect, but an agent has enough to act correctly.

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 schema already documents all four params (baseline 3). The description adds meaning by tying options/living_people/incl_private to the tool's exclusion default and explicitly contrasting it with Gramps' default, which clarifies the semantics of those flags beyond the schema text.

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?

States a specific verb+resource ('Generate a report and return the file it produced') and names what it returns, which lets an agent distinguish it from list_reports/get_report_options (which enumerate rather than generate). The action is unambiguous.

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?

Gives clear operational context: it usually runs in the background and the task_id should be polled with get_job, and it documents the default privacy filtering. It lacks an explicit 'call list_reports first' instruction and any when-not-to-use statement, so it stops short of full guidance.

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