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

Annotations only declare the safety profile (not read-only, non-destructive, open-world); the description adds genuinely new behavioral context: the call is stateless and returns feasibility, price/risk notes and an optional alternative. It stops short of saying whether anything is persisted or what happens on an infeasible adjustment.

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 tightly packed sentences: purpose first, return shape second, calling constraint third. Zero filler and nothing buried.

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 summarizes the return payload, and it flags statelessness for a nested-object input. Remaining gap is what the proposal object must contain and error/feasibility-failure behavior, but an agent has enough to invoke it correctly.

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 carries the burden: it names five of the eight adjustment knobs (review level, model tier, volume, budget cap, disable steps) and clarifies that the proposal argument must be the full proposal JSON. It omits hourlyRateSek, taskDescription and consultantHoursPerMonth, and gives no detail on adjustment interaction semantics.

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 and resource ('Adjust an existing proposal') and enumerates the adjustable dimensions, so an agent knows exactly what the tool mutates. It is distinguishable from start_proposal/get_proposal by the word 'existing', but no sibling is named explicitly.

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 'Stateless — pass full proposal JSON' note gives a usable calling convention, implying this is for re-evaluating a proposal rather than creating one. However, it never states when to prefer this over start_proposal or estimate_automation, nor any prerequisites or exclusions.

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