check_diagonal_weights

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

With no annotations provided, the description carries the full behavioral burden. It clearly states that glyph colors are not modified by default, and only marks colors when mark_glyphs=True, specifying the color scheme (red/yellow/green). It also discloses the default scope for master_id and glyph_names. This is transparent about side effects. It does not mention whether the operation is read-only or if it returns a report, but the existence of an output schema covers that. Slightly more could be said about error behavior or non-mutating nature, but it's well above average.

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 well-structured: a one-line summary, followed by a detailed breakdown of what is measured and checked, then default behaviors, then side-effect disclosure, and finally an Args section. The information is front-loaded with the core purpose. It is slightly longer than necessary but every sentence adds value; no filler or tautology.

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 check tool with an output schema (which presumably defines the return format), the description covers the essential aspects: the checks performed, the glyph scope, the master scope, and the marking behavior. It does not describe the exact output structure (left to schema) nor discuss performance or edge cases like empty results, but given the complexity and that all parameters are optional, the description is sufficiently complete for an agent to invoke it 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 0%, so the description must fully compensate. It does so with an explicit Args section explaining each parameter: glyph_names (optional list, defaults to all), master_id (empty = all masters), mark_glyphs (colors only when explicitly requested). It also adds meaning beyond the schema by explaining the effect of each parameter and the defaults. This is exemplary compensation for a sparse 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 opens with a clear, specific statement: 'Check diagonal stroke weight consistency and ratio to vertical stems.' It enumerates the exact glyph set (V, A, W, X, Y, Z, etc.) and defines the two checks (consistency of related groups, ratio within professional range). This clearly distinguishes it from sibling check tools like check_overshoots or check_related_forms, which focus on different aspects. The purpose 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?

The description explains the default behavior when parameters are omitted (checks all diagonal glyphs, analyzes all masters) but does not explicitly guide when to use this tool versus alternatives. With 50+ sibling tools, many of which are also checks, the absence of any 'use this instead of X' or 'when not to use' guidance is a notable gap. The defaults are useful context but not full usage differentiation.

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