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

With no annotations provided, the description carries the burden of behavioral disclosure. It explains signature placement ('in erkannte Signaturfelder gesetzt oder per manualPlacement platziert') and the purpose of lang for non-Latin fonts. It does not cover error handling, permission requirements, or the fact that the original PDF is not modified (only a new base64 is returned).

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 description is three sentences, front-loads the core purpose, and then succinctly clarifies the two main sub-behaviors (answers and signature). No redundant or filler wording.

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?

Given a complex tool with 7 parameters, nested objects, and no output schema, the description covers the primary purpose, signature flow, and optional language handling. It omits details about extraText and filename, but these are secondary and adequately described in the schema. The description is sufficient for an agent to understand when and how to use the tool.

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?

Even though schema coverage is 71%, the description adds significant meaning: it ties answers to inspect_pdf, clarifies the relationship between signaturePngDataUrl and manualPlacement, and explains lang's role in font selection. These are insights not directly inferable from the schema alone.

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 phrase 'Ein BELIEBIGES (nicht-Katalog-)PDF ausfüllen und optional signieren' clearly identifies the tool's function: fill any non-catalog PDF and optionally sign. It distinguishes from catalog-specific siblings like fill_template and specifies the output as a base64 PDF.

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 description specifies the tool is for non-catalog PDFs and directs users to obtain field names from inspect_pdf ('answers = Feldname→Wert (aus inspect_pdf)'), implying a prerequisite workflow. However, it does not explicitly name alternative tools like fill_template or state when not to use this tool beyond the catalog exclusion.

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