analyze_kerning

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

With no annotations provided, the description carries the full burden and handles it well. It discloses that the tool returns a formatted markdown report, does not modify glyph colors by default, and only colors glyphs when mark_glyphs=True. It also clarifies the cross-master behavior of master_id. This is transparent about side effects and scope.

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 appropriately detailed for a complex analysis tool. It is front-loaded with the core purpose, then uses a bulleted list for checks and a compact Args section. Every sentence earns its place, including the recipe pointer and side-effect note.

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 the tool has no annotations and multiple behavioral nuances, the description covers the key aspects: input parameters, side effects, checks performed, and return format. An output schema exists, so not detailing the full report fields is acceptable. Minor gaps remain, such as not mentioning whether the analysis requires any permissions or what 'verdict' precisely means, but overall it is complete enough for correct invocation.

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 for the bare schema. It does: master_id is explained as optional with cross-master checks always running across all masters, and mark_glyphs is explained as coloring glyphs by verdict only when explicitly requested. This adds real meaning beyond the schema's titles and defaults.

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 and resource: 'Analyze kerning quality across all masters.' It enumerates exactly what checks are performed (missing pairs, sign changes, outliers, redundant exceptions, group orphans). However, it does not explicitly differentiate itself from the nearby sibling analyze_kerning_groups, which could overlap on the group-orphans check.

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 gives useful context: for kerning from scratch, call get_recipe('kerning_from_scratch') first, which implies this tool is for analyzing existing kerning rather than creating it. However, it does not explicitly state when to use this tool versus alternatives like analyze_kerning_groups or get_kerning, and there are no clear exclusion conditions.

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