crystal_stats

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

No annotations exist, so the description carries the full burden. 'Compute and inspect' strongly implies a non-destructive read, and the global-vs-filtered framing conveys scope, but nothing is said about cost/performance, whether results are cached, or permissions. It signals read-only behavior implicitly rather than explicitly.

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?

It is a single front-loaded sentence with the verb first, which is good. However, the clause stack ('temporal genesis', 'structural totals', 'physical disk footprints', 'quantitative prompt token savings') is jargon-heavy and overlapping, adding length without sharpening meaning.

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?

For a 13-parameter analytics tool with no annotations and no output schema, the description covers the broad purpose and scoping but omits any indication of the returned structure, which the json_output param implies is selectable. Adequate as a minimum-viable statement, but it leaves real gaps for such a complex tool.

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%, so the 13 parameters are already fully documented in structured form, establishing a baseline of 3. The description adds only the high-level notion of 'filtered search criteria' and global scope, contributing no syntax or semantics beyond the schema.

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 names a specific verb ('compute and inspect') and resource ('workspace cave statistics'), and enumerates the metric families it returns (disk footprints, token savings, structural totals). An agent can distinguish it from crystal_search (which retrieves crystals) because this tool aggregates rather than lists. It stops short of explicitly naming siblings or contrasting scope, keeping it below a 5.

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?

It hints at two modes ('global cave or filtered search criteria') but never states when to reach for this tool over crystal_search or crystal_triage, nor when filtering is preferable. There are no exclusions or prerequisites given. Usage must be inferred entirely from the name and param list.

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