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

Annotations only give readOnlyHint=false, destructiveHint=false, openWorldHint=true. The description adds real behavioral context beyond that: it returns the report ID, no one is notified until submit, the draft remains editable and deletable, and it requires a Cotlet API key with app access.

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?

Front-loaded with the core action and well-organized, but slightly padded by the awkward clause 'so it does not wait for your OK.' Most sentences earn their place by carrying workflow and lifecycle information.

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?

No output schema exists, and the description compensates by stating the tool returns the report ID. Combined with the lifecycle and notification behavior, an agent has everything needed to call it correctly and understand the follow-up path.

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 100%, so both parameters (workspace, title) are already documented in the schema. The description restates workspace scoping ('the workspace you name') but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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: 'Creates an empty draft report in a workspace.' It distinguishes itself from siblings by naming add_expense_to_report and submit_report as the follow-up steps, so an agent can tell this is the report-creation step rather than the expense-add or send step.

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?

Explicitly describes the workflow position: create the draft here, add expenses with add_expense_to_report, then send with submit_report. It also notes nobody is notified until submission, which tells the agent when this tool is the right (safe, reversible) entry point.

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