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

Annotations already establish this as a safe read-only, idempotent, closed-world operation, and the description still adds substantial behavioral detail: what limitsNote reports, the exact coneFit verdicts ('cooler', 'hotter', 'fits', 'skipped') and their conditions, the weak 'soft' strength for cone 6 vs 10, that 'fits' is not a pass, and that Stull regions shift with cone/flux. The closing caveat that these are published-figure cautions, not a test or food-safety guarantee, is exactly the kind of expectation-setting an agent needs.

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 one dense paragraph with long parenthetical asides and trailing ellipses ('rising expansion...'), and the cone-12-and-up no-limits fact is asserted twice. Most sentences do carry real information, but the lack of front-loading and grouping by parameter/return field makes it harder to scan than it needs to be.

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 complex tool with nested objects and no output schema, the description does substantial work by naming the returned concepts (limitsNote, coneFit with verdicts, strength, stull) and their interpretation. It stops short of a full return-value description, so an agent still infers the overall response shape, but nothing essential for calling it correctly is missing.

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 every parameter, including the nested firing object and limitSet defaulting, is already documented in the schema. The description reinforces consequences (leaving firing out, no limits from cone 12 up, limitSet falling back to account preferences) but adds little syntax or semantics not present in the schema. Baseline 3 applies when the schema does the heavy lifting.

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 clause gives a specific verb and resource: 'Checks a glaze recipe for what is past a recommended limit for its firing', and it enumerates the limit categories (boron, alkali, alumina, clay, expansion). It also distinguishes itself from analyze_recipe by noting stull is reported 'as analyze_recipe gives it'. The core purpose is clear, though the surrounding clauses about coneFit and Stull caveats dilute the focus.

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 rich applicability context: which cone bands are checked, that 'top' band limits are not checked, that coneFit returns 'skipped' for lead/lithium/raku and cones 01-3, and that limitSet choices come from account settings. What it never frames explicitly is a routing rule against siblings (e.g. when to call check_limits versus analyze_recipe), so the guidance is contextual rather than directive.

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