compare_stems

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

With no annotations, the description carries the full burden, and it delivers: it explicitly states that glyph colors are not modified by default, describes the exact color meaning of each verdict, explains per-master vs. all-master behavior, and clarifies that mark_glyphs only colorizes when explicitly requested. This is unusually transparent about side effects.

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?

The description is long but well-structured with labeled sections (RECIPE, verdicts, groups, master behavior, color behavior). Every major block earns its place for a fairly complex analysis tool; the glyph-class enumeration is detailed but useful. It is slightly longer than strictly necessary, so not a 5.

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?

Given that an output schema exists, return-value documentation is not needed. The description covers inputs, output semantics via verdicts and per-master results, side effects, and the recommended recipe path. An agent has everything needed to select and invoke this tool 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 description coverage is 0%, so the description must compensate—and it does thoroughly. It explains glyph_names as the list to compare, master_id as optional (empty = all masters), and mark_glyphs as the explicit color-marking switch. This gives agents full semantic understanding beyond the raw JSON 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 opening line states a specific verb and resource: 'Compare stem thicknesses across multiple glyphs to find inconsistencies.' This clearly differentiates it from measurement-only or single-glyph tools, and the detailed verdict/group taxonomy reinforces what the tool produces.

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 explicitly recommends get_recipe('audit_consistency') for a full font audit, giving agents a clear alternative workflow. It also explains when to use master_id vs. omitting it. It stops short of naming sibling tools like measure_stems and saying 'use this instead of that,' but the recipe pointer and mode behavior provide solid guidance.

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