Program statistics from reports

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

No annotations are supplied, so the description bears the full burden. It conveys read-only aggregation over 'visible' reports and reveals the shape of the computed output, but says nothing about permissions, cost/rate limits, caching, or whether 'visible' depends on the caller's access level.

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?

A single dense sentence with the resource front-loaded and the output contents enumerated after the colon; nothing is wasted. It is long but every clause is informative, so it stops just short of maximal efficiency.

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 usefully sketches the return contents (yearly and severity breakdowns, top researchers), which is the main thing an agent needs. Minor gaps: no mention of what 'visible' means or of response size/pagination, but the core is covered.

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 description coverage is 100%, with both `program` (slug/fragment/URL accepted forms) and `years` (1-20, default 6) fully documented in the schema. The description adds no further parameter semantics beyond hinting at the yearly breakdown, so the baseline of 3 applies.

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 opens with a specific verb+resource ('Aggregated statistics computed from all visible reports of a program') and then itemizes exactly what is aggregated: totals/averages of payouts, reports, money per year, per asset severity, and top researchers. This clearly separates it from siblings like list_reports or top_hackers, though no sibling is named explicitly.

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?

Usage is only implied: 'all visible reports of a program' suggests this is the roll-up view over a program's report corpus, in contrast to per-report tools. There is no explicit when-to-use/when-not guidance and no named alternative (e.g. 'use get_program for metadata, this for aggregates').

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