settle_decision

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

With no annotations, the description carries the full load; it does add real behavioral context by disclosing that returns are recomputed from prices rather than taken from the caller, which is the key non-obvious trait. It omits other important behavior for a write tool: whether the decision must pre-exist, whether a prior settlement is overwritten, and what happens if trade_date does not match a logged decision.

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 with no waste: purpose first, then the division of labor on inputs, then guidance on reflection content. Every sentence contributes something the agent would not otherwise know.

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?

An output schema exists, so return values need no explanation, and the description covers purpose, caller responsibility, and content guidance. The gap is behavioral: for an unannotated mutation tool it should say whether this creates a new settlement record or updates an existing one and what precondition applies.

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 compensate, and it does only partially: it explains the expected form and content of 'reflection' well. Neither 'ticker' nor 'trade_date' is given meaning — notably whether trade_date is the original decision date that must match an existing record — leaving the agent to guess on two of three required parameters.

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's outcome and your reflection in the memory log,' and clarifies that return figures are computed by the server, not supplied by the caller. It is distinguishable from read-only siblings like past_decisions, though it never explicitly names unsettled_decisions or past_decisions as the counterparts.

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 by the framing (this is where a pending call gets closed out), and the 'only the reflection comes from you' clause usefully scopes what the agent must supply. However, there is no explicit statement of when to prefer this over siblings such as unsettled_decisions or memory_lessons, and no stated prerequisite that the decision must already exist unsettled.

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