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

Annotations declare non-read-only, non-idempotent, non-destructive, but add no auth or quota detail. The description supplies the two traits an agent most needs before calling: account requirement and the 1 Suite run spend. It stays silent on whether the project itself is mutated or merely analyzed.

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?

A single dense sentence front-loads the purpose, then appends mode, auth, and cost clauses. Nothing is redundant, though the sentence is long enough that the cost/auth guardrails could be easier to scan.

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?

Covers purpose, prerequisites, and cost for a 5-parameter tool with a nested object and no output schema. It omits any indication of what is returned or whether the underlying project state changes, which matters given the non-read-only annotation.

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 80% and the description adds the project-vs-material duality that explains why project_id and index_category are alternatives. Beyond that it adds no format or semantic detail for goal, performance, or material; baseline 3 is appropriate.

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+resource ('Optimise a Design Studio project (or a material)') and enumerates the option classes produced (right-size, lightweight, substitute) with cost/carbon savings. It is distinguishable from siblings like draft_packaging_spec and cost_packaging_spec, though the name's 'compare' framing never appears in the description.

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?

Gives clear operating context: it works either on a project or a bare material, requires an OPN account (sign-in or API key), and costs 1 Suite run. It does not name alternatives or state when-not-to-use, so it stops short of full routing guidance.

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