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

Annotations already declare readOnly/idempotent/non-destructive/non-open-world, so safety is covered. The description adds genuinely useful behavior the annotations cannot: the exact return contents (flour, water, starter, salt) and the fact that a loafy.ai link is included for adjustment and timers.

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?

Two sentences, no filler, with the calculation purpose front-loaded and the return value stated second. Every clause carries information an agent would otherwise have to guess.

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?

With no output schema, the description correctly steps in to describe the returned values and the external link, which is what an agent needs to chain this tool. The only small gap is that whole_grain_percent is a parameter never acknowledged in the description.

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% and the property descriptions are unusually rich (loaf_size_g explains flour-vs-dough-weight with a worked example). The description restates three of the four inputs and omits whole_grain_percent, so it adds little beyond the schema; baseline 3 applies.

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?

States a specific verb (calculate) and a specific resource (sourdough bread recipe), plus the three driving inputs, so an agent knows exactly what comes out. It does not differentiate itself from the sibling calculate_pizza_dough or from plan_sourdough_bake, so it stops short of 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?

There is no when-to-use or when-not-to-use guidance and no named alternative, even though calculate_pizza_dough and plan_sourdough_bake are close siblings. Usage is only inferable from the verb 'Calculate', which is the same level of guidance as the mid-tier calibration example.

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