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

Goes beyond the annotations by stating what it does NOT do ('books nothing and sends nothing to anyone'), that it can run without confirmation, and that it needs the user's Cotlet API key with access to this app. These are meaningful behavioral facts an agent needs to act safely.

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 mostly tight, but the phrase 'returns its document_id and inbox status unused' is awkward and slightly obscures the return meaning.

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?

With no output schema, the description covers the return values (document_id, inbox status), the non-destructive behavior, and the auth requirement. Nothing essential for correct invocation is missing.

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 all three parameters are already documented. The description adds only marginal detail ('one file', 'an https link the agent can reach'), so the 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 ('Put a receipt or supplier invoice in the Fiken inbox') and clarifies the scope ('so it can be attached to a purchase'). It is clearly distinguishable from the sibling create_purchase, which it names as the downstream consumer.

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: the document waits in the inbox until create_purchase or a person uses it, and it 'runs without asking first' (no confirmation needed). This gives the agent both the when-to-use and the relationship to the alternative.

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