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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses that paging requires following BOTH returned cursors, that Investboard-originated checks are absent from results, that outcomes are investor-reported and never establish execution, that saved verdicts keep original evidence dates, and that linked_decision is computed on read and never stored. These are substantive behavioral facts an agent could not infer from annotations alone.

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?

Purpose is front-loaded in the first sentence, followed by usage, paging, and scope caveats in a logical order. The final sentence on linked_decision is long and heavily qualified ('never an instrument and never a value'), which is partly redundant given an output schema exists, but it still carries non-obvious derivation semantics.

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 four optional parameters, full annotations, and an output schema, the description covers scope, paging discipline, and confidence semantics well. Minor gaps remain: default ordering, whether id is an exclusive filter or combinable with cursors, and the meaning of 'limit' are not addressed.

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 only 25% (only id is documented), so the description must compensate — and it does for the paging pair: 'before' and 'before_id' are revealed as two returned cursor values that must be followed together. 'id' semantics are reinforced via agent_reflection_id. 'limit' and the exact cursor ordering remain undocumented in either place.

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: list the longitudinal audit of actions checked by an assistant plus their verdicts, scoped to the connected user. That is clearly distinct from the mutating sibling check_action and from get_journal, and the mention of 'agent_reflection_id' from a journal entry links the two resources. It stops short of explicitly naming a sibling it must not be confused with.

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?

'Use id to read the check named by a journal entry's agent_reflection_id' gives a concrete trigger condition, and 'Follow both returned cursor values when paging' tells the agent how to continue. The exclusion 'Checks made in Investboard itself are not listed' bounds expectations. No explicit when-not-to-use versus check_action is stated.

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