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

Annotations only give hints (readOnlyHint=false, destructiveHint=false), but the description goes further: it explicitly states 'This WRITES financial data' and describes the atomic sequence of operations (mark reviewed, write journal lines, audit trail, queue sync). It also discloses that reason is stored verbatim and that actor_id must belong to the org. This adds behavioral context beyond annotations, with no contradiction.

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?

The description is dense but every sentence carries essential information: the main action, the atomic effects, the warning about financial writes, the failure conditions, and the parameter defaults. It is front-loaded with the action and consequences, and there is no fluff. Despite its length, it is highly efficient.

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?

The tool has an output schema (not shown in the prompt), so the description does not need to explain return values. It covers prerequisites, atomicity, audit trail, ledger sync, failure scenarios, defaults, and constraints on actor_id. It also references the sibling get_unreviewed_events for context. Everything an agent needs to call it correctly is present.

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 100%, so the schema already documents each parameter thoroughly (including defaults and allowed account codes). The description adds some usage context (e.g., 'only call with an account you are confident in' and the default for org_id), but it mostly reinforces the schema's content rather than adding new semantics. Baseline 3 is appropriate given high schema coverage.

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 ('approve'), a precise resource (one event from the review queue), and the action's effects (assigns account, writes journal lines, audit trail, queues ledger sync). It clearly distinguishes this from siblings like get_unreviewed_events and list_chart_accounts by focusing on the approval action and its side effects.

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 explicitly tells the agent when to call it (only with a confident account) and mentions the prerequisite of pulling items from get_unreviewed_events. It also states failure conditions (event not existing, wrong org, already approved) that guide when not to use it. It even warns that it writes financial data, implying caution. This is clear usage guidance beyond mere purpose.

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