Draft Expense Report

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

Annotations already declare non-destructive, non-readonly, non-idempotent write semantics. The description adds meaningful context the annotations do not: the result is a DRAFT that is not submitted, and it includes a compliance check. This is exactly the kind of write-side clarification that helps. Not a 5 because it does not mention persistence/visibility of the draft or whether it can be edited/regenerated afterward.

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?

One tight sentence front-loads the action ('Create a DRAFT'), then states the return ('return it with a compliance check'), then the crucial non-effect ('Nothing is submitted'). No wasted words.

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?

Output schema exists, so return-value details needn't be spelled out, and annotations cover the safety profile. The description covers the essential non-obvious behavior (draft-only, compliance check). A small gap remains around lifecycle — what happens to the draft afterward, and whether re-calling duplicates it (idempotentHint=false).

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 67%; the schema already documents 'month' (default = current month) and 'txn_ids' (omit to include all). The description adds nothing about parameters, so it merely repeats the tool purpose. Baseline 3 given moderate schema coverage with the key semantics documented in the schema itself.

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?

Specific verb (Create) + resource (draft expense report) + scope ('Nothing is submitted') clearly distinguishes it from the submit_for_approval sibling. 'DRAFT' and 'return it with a compliance check' tell an agent exactly what this does versus the other approval-related tools in the list.

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?

The phrase 'Nothing is submitted' implicitly routes the agent here when draft-only behavior is needed, versus submit_for_approval. But no explicit 'use X instead when ready to submit' statement is provided, so an agent must infer the boundary from the sibling name.

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