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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond them: fractional rollback semantics, tie listing, branch-cost rule, validation refusals naming the offending node and sum, a 300-node cap, the concrete return artifacts, and the ~1 hour expiry on large-tree download links. That is exactly the operational context annotations cannot carry.

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?

It is a single dense paragraph but front-loaded with the trigger condition and free of filler; each sentence adds scope, input, output or a limit. The size is justified by the tool's complexity, though a short bulleted split of inputs vs. guarantees would scan faster.

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 7-parameter combinatorial tool with an output schema, the description covers input modes, limits (300 nodes), failure modes, output artifacts and link expiry. Nothing an agent needs in order to call it correctly appears to be missing.

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 coverage is 100%, so the baseline is 3; the description earns one more by framing outline and nodes as alternative input modes for the same tree (an either/or relationship the schema lists as two independent properties). It also flags that costs are applied 'by a stated rule', though it does not state the rule, leaving some ambiguity.

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+resource pair ('decision tree drawn or solved') and enumerates the concrete inputs and outputs (rollback with expected values, chosen option, PDF/SVG/CSV). It never names the sibling check_tree, so an agent must infer the boundary between 'make' and 'check' on its own, which keeps this out of the top band.

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 explicit trigger phrases ('which option has the higher expected value', 'draw a decision tree for launching this product') and a clear scope exclusion ('does not estimate probabilities or give advice'). It does not name alternatives or say when to prefer check_tree instead, and the built-in validation refusal partially overlaps what a check tool would do.

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