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

Beyond the annotations (destructiveHint=true, idempotentHint=false, readOnlyHint=false), the description adds real behavioral facts: the contract status becomes signed afterward, and the stored file is never replaced, which explains the irreversible, destructive nature flagged by the annotations. It does not cover permissions requirements, file size limits, or what happens on a repeat or conflicting call, which is why the score is not 5.

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, front-loaded with the core action and format constraints, then the post-condition and irreversibility. No filler or redundant restatement of the title.

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 4-parameter mutation with no output schema and low schema description coverage, the description should explain signed_on, note that the call fails or is rejected for already-signed contracts, and ideally indicate whether the call returns anything. The behavior it does describe is solid, but these gaps leave the definition only partially complete.

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 only 25%, and the description compensates partially by specifying that the payload is base64 and listing accepted formats (pdf, jpg, png), which clarifies the extension enum and file_base64. Yet id is only defined in the schema as 'Vertrags-ID', and signed_on is never explained anywhere, an important gap for a signing date parameter.

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 description uses a specific verb and resource: it stores the signed contract PDF/JPG/PNG, base64-encoded, for an issued contract. It also states the resulting state (status signed) and that the file is never replaced, so an agent can tell it apart from send_contract, issue_contract or download_contract_pdf, though no sibling is named explicitly.

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 'zu einem ausgestellten Vertrag' implies the prerequisite that the contract must already be issued and that this is the step after issuing and sending. However, the description gives no explicit when-not guidance, such as what to do if the contract is already signed or how this differs from revise_contract or update_contract.

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