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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true and idempotentHint=false, so the write semantics are covered structurally. The description adds genuinely new information the annotations cannot convey: API credit costs (10 per create, 50 per invoice) and a limited monthly quota, which directly affects whether an agent should batch or retry. Minor gap: it doesn't say a retry creates a duplicate project.

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?

Two short sentences: the first front-loads the action with a 'WRITE:' marker, the second carries the cost warning. No repetition of schema content and nothing extraneous.

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 cost/quota disclosure covers the main non-obvious risk for a 9-parameter write tool. But with no output schema, the description should say what comes back (presumably the created project and its id) so the agent knows how to chain follow-up calls; that gap is left entirely to guesswork.

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 all nine parameters, including enum values, date formats, and the budget_type/budget_time branching, are documented in the schema itself. The description adds nothing beyond the fact that a customer is involved, so the baseline 3 applies.

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 verb+resource pair ('create a project') is explicit, and the 'WRITE:' prefix immediately separates it from the get_/list_ siblings such as papierkram_get_project and papierkram_list_projects. It stops short of naming an alternative tool, but the create/get/list split is unambiguous.

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?

'create a project for a customer' implies the usage context (a customer must already exist), and the schema points to papierkram_list_companies for customer_id. However, there is no explicit when-to-use/when-not statement or reference to papierkram_update_company-style siblings for later edits, so usage is only implied.

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