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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description's addition that the tool 'compares and returns a verdict' does not contradict. The description adds context about the computation (take-home pay after deductions) but no new behavioral traits beyond what annotations provide. No contradiction found.

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 efficiently written in two sentences plus a standalone statement, front-loading the purpose. Every sentence adds value, with no repetition or fluff. It could be slightly improved by structuring parameter hints, but overall it is well-organized for its length.

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's high complexity (3 top-level objects, many nested fields, no output schema), the description is incomplete. It explains the return value ('one-line verdict plus a link') but provides no guidance on input structure or how the complex schema maps to the described factors (e.g., commute, 401(k)). The agent would struggle to invoke the tool correctly without schema descriptions or more detailed help.

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%, meaning no property descriptions exist in the schema. The description only says 'Accepts only numbers and enums,' which is insufficient for a complex nested object with many fields like 'current', 'offer', and 'options'. It fails to explain what parameters like 'commute', 'filingStatus', or 'retirementContributionPercent' represent, leaving the agent unable to correctly populate inputs.

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 clearly states the tool's purpose: 'Compares two jobs on real take-home pay after federal, state, FICA, 401(k) and commute, and says which wins and by how much.' The verb 'compares' and resource 'jobs' with the specific financial factors make the function distinct from sibling tools like 'best_filing_status' or 'roth_vs_traditional'.

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 implies the tool is used for comparing job offers but does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. It lacks guidance on prerequisites or when not to use it, relying on implicit differentiation from sibling tool names.

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