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

'Write-once per check' is real behavioral disclosure beyond the annotations: a repeat call will not overwrite, which an agent needs in order to avoid treating this as an update path. The explicit disclaimer that no order is placed/changed/transmitted adds safety context the destructiveHint annotation alone does not convey. It omits what an agent should expect on a second attempt (error vs. silently ignored) and does not mention that records cannot be removed.

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 short sentences, front-loaded with what gets written, then the write-once constraint, then the safety disclaimer. Every sentence adds information; nothing repeats the title or schema.

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 an output schema present, return values need no explanation, and the description covers the essential traits: mutation, write-once, no order side effects. It leaves open what happens when the check_id does not exist or a decision was already recorded, which matters for a non-idempotent write.

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 must carry parameter meaning, and it partially does: it enumerates the three outcomes, marks the note and broker reference as optional, and implies the check linkage. It never mentions check_id as a required UUID identifying which check the decision attaches to, nor the length bounds, so the highest-value required parameter is left to the schema alone.

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 (record a decision) plus the exact domain of values (proceeded, abandoned, deferred). The closing sentence sharply distinguishes it from any order-execution capability and, implicitly, from the read-only siblings such as get_journal or check_action.

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?

'Record what the investor decided after a check' gives clear timing context: call it after a check exists. The exclusion ('never places, changes or transmits an order') rules out a tempting misreading. It does not name a sibling alternative or state what to do if the decision is later revised, so it stops short of 5.

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