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

Annotations already mark it read-only and non-destructive. The description reinforces this by stating 'Returns proposals only — nothing is created.' It also adds context about the input source (recent posted transactions) and the contents of each proposal, exceeding what annotations alone provide.

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 focused sentences. The first sentence states the core action, the second clarifies the workflow and non-mutating nature, and the third lists proposal contents. No redundant wording or repetition of schema details.

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?

Given the output schema exists (so return values are structured separately), the description fully covers purpose, workflow, and relationship to sibling tools. It tells the agent exactly what to do with the result, making invocation and follow-up clear.

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?

The schema has only companyId with a minimal 'UUID value wrapper' description. The tool description implies companyId selects the company whose transactions are scanned, adding partial meaning beyond the schema. Since schema coverage is 100% but thin, this is a baseline 3 with some added context from the description.

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 clearly states it scans recent posted transactions and suggests accrual schedules. It distinguishes itself from accounting_create_schedule by explicitly noting that nothing is created until confirmed, so the agent knows this is a proposal-generation tool, not a mutation.

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?

Provides explicit guidance: use this to get proposals, then call accounting_create_schedule to confirm. The example (amortize a prepaid) clarifies typical use. This directly tells the agent when to use this tool versus the create alternative.

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