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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so safety is covered. The description adds real value beyond that: it states the verdict is favorable/unfavorable, that breaking points, permitted repairs and verification priorities are returned, and that a zero limit acts as a hard lock. It does not describe failure behavior for mismatched modes or malformed inputs, keeping it below a 5.

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?

Three sentences, front-loaded with the purpose and the covered scenarios before the return summary and the scope disclaimer. Every sentence carries information; the only mildly expendable element is the phrasing about 'original bounded workflow models,' which is promotional rather than operational.

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 tool with five mutually exclusive mode branches and roughly twenty parameters per branch, the description gives an accurate high-level orientation, plus return contents and lock semantics, leaving field-level detail to a very thorough schema. The gap is that terms like 'permitted repairs' and 'verification priorities' are undefined and there is no output schema, so the agent cannot anticipate the result shape precisely.

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?

Reported coverage is 0% only at the top level; the nested per-mode properties in fact carry very detailed descriptions, so the schema does most of the semantic work. The description contributes by naming the five workflows, which helps the agent pick the correct oneOf branch, but it adds no units, defaults or format guidance beyond what the schema already supplies.

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 plus resource and enumerates the five decision types it covers (job, restaurant run, delivery route, equipment purchase, staffing plan), which maps directly onto the schema's five mode branches. It does not explicitly distinguish itself from siblings such as buscalc_break_even_sales or buscalc_markup_vs_margin; the contrast (multi-constraint feasibility vs. single-formula calculation) must be inferred.

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?

Usage is implied by the scenario list and by 'Zero permitted change locks an item,' which tells the agent that a zero input means 'not permitted to change.' The closing clause ('no world-first, forecast or obtainable-saving guarantee') functions as a scope boundary telling the agent not to use this for forecasting, but no alternative sibling is ever named when a single calculation suffices.

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