Soxoa Automation Planner

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

Annotations already declare this as a safe read-only, idempotent, closed-world computation, so the safety profile is covered. The description adds meaningful behavior beyond that: the server-side defaults (60% automatable share, 48 working weeks), the requirement to preserve user-supplied values, the "do not invent assumptions" guardrail, and the illustrative-not-guaranteed framing. It does not describe output shape, though the output schema covers that.

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?

Four tight sentences, front-loaded with the purpose before the operational rules and the disclaimer. Every sentence carries actionable content, with only minor overlap between the default-value sentence and the schema defaults.

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 read-only estimation tool with a rich output schema and 100% schema coverage, the description supplies everything an agent needs: the input contract, default behavior, how to handle missing values, and the interpretive limits of the result. Return values are appropriately left to the output schema.

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 defaults, bounds, and the omit-vs-preserve rule is already documented in the schema. The description restates the default values for automatableShare and workingWeeks but adds no new syntax or format meaning. This is the baseline 3 where 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 description states a specific verb and resource: "Estimate reclaimable team capacity and illustrative payback from user-supplied workload assumptions." An agent immediately knows this produces a capacity/payback estimate from supplied workload inputs. It does not, however, name or contrast itself with the sibling prioritize_automation_workflows, so differentiation is left to inference.

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?

It gives clear usage context ("Use for operational planning") and an explicit exclusion ("not guaranteed savings or financial advice"), plus operational rules for when to omit optional inputs versus ask for missing required ones. The one gap is that it never points to the sibling tool as an alternative for prioritization tasks.

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

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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description adds real context beyond them: the 1–12 ranking scale, the classification output, and the important instruction to solicit missing facts rather than fabricate values, which is a meaningful behavioral constraint.

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 tight sentences: ranking behavior first, required inputs second, and the missing-facts rule last. Every sentence carries information and nothing is repeated from the schema or annotations.

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 an output schema present, return values need not be described, and annotations cover the safety profile. The description adequately covers inputs and behavior; the only gap is the absent connection to the sibling tool and the ranking criteria's relation to it.

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, and it does by naming all six required workflow facts (weekly hours, predictability, judgment required, error cost, data sensitivity, system count) that match the schema properties. It omits the enum value sets and the 12-item cap, but the core field meaning is conveyed.

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 ('Rank 1–12') and resource ('user-described workflows') along with the scoring dimensions and the three output verdicts (automate, assist, discovery). It never mentions or differentiates from the sibling tool estimate_automation_roi, 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?

It implicitly indicates when inputs must be gathered ('Each workflow requires caller-supplied weekly hours...') and gives a behavioral instruction to 'Ask for missing facts rather than inventing values,' but there is no explicit when-to-use vs. estimate_automation_roi guidance or when-not-to-use condition.

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