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

Goes well beyond the annotations by disclosing the actual side effect (withdrawing an approval before anything ran) and the reversibility path (re-approving re-opens it) — neither of which readOnlyHint=false / destructiveHint=false conveys. It stops short of describing what happens to a pending decision or whether the operation requires specific permissions.

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 with the core effect front-loaded, which is efficient. The CLI-twin parenthetical is marginally useful for cross-referencing but is the least load-bearing part of the sentence.

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 two-parameter mutation with no output schema, the description covers the essential agent-facing facts: what state change occurs and that it is reversible. Only minor gaps remain, such as which decision states are eligible and any permission requirements.

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 both parameters are already documented, including that decision_id comes from list_cost_decisions. The phrase 'with your reason' adds a little meaning about the note's purpose, but also implies it is expected even though the schema marks it optional.

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 ('set aside') and resource ('cost decision'), and the parenthetical ties it to the CLI command `ankra cost decisions set-aside`, which pins down the operation precisely. It does not explicitly separate itself from nearby siblings like hold_cost_decision or release_cost_decision, so an agent must infer the distinction.

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?

Usage is implied through the state-transition note: setting aside an approved or held decision withdraws the approval. The sentence 'Approving it again re-opens it' gives recovery guidance, but there is no explicit when-not-to-use clause or pointer to hold_cost_decision/release_cost_decision as alternatives.

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