Create expense

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the safety profile is known. The description adds genuinely non-obvious behavior: the expense feeds the project's job costing (a downstream side effect), the project is hard-required and rejected without one, the actor is the signed-in user, and no receipt file is attached. It does not address duplicate creation despite idempotentHint=false, which is the one material gap.

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 leading sentence is front-loaded with verb, resource and key fields, and the second sentence carries the behavioral detail. There is some duplication, since the field list appears in the first sentence and is re-enumerated in the second, but the total length is reasonable for an 8-parameter mutation.

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?

For a non-idempotent create with 8 params and no output schema, the description covers the essentials: required project, actor identity, job-costing side effect, absence of receipt upload, and an explicit return statement ('Returns the saved expense'). Remaining gaps are duplicate handling and post-creation editability.

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 75%, so the schema already carries most parameter meaning (currency, enum values, vendor_id -> contact_id, project_id requirement). The description mostly restates the field list ('name, amount, date, vendor, project, cost type, reason and whether it is billable') rather than adding semantics beyond it; only 'no receipt file is attached' clarifies an absent field.

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 ('Records an expense') and enumerates the domain fields (receipt, purchase, fee; amount, date, vendor, project), so the agent knows this is a create operation aimed at cost entry, not a listing or retrieval. It does not explicitly contrast with create_bill or create_purchase_order, which are the genuinely confusable siblings in this domain, so it stops short of a 5.

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?

Gives useful preconditions: 'The project is required by the app' and 'No receipt file is attached', plus it runs 'as the signed-in user'. But it never says when to choose this over create_bill / create_purchase_order, which matters because all three create cost records in the same product. Usage is implied rather than routed.

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