Sign PDF with an image

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

Adds real behavior beyond the annotations: default background removal so scanned signatures sit cleanly, rotation-aware coordinates, a threshold-controlled transparency rule, and a default output location (server temp folder unless --out-dir is set). The one unaddressed tension is that the tool writes a new output file while annotations declare readOnlyHint=true; the description does not clarify that the source PDF is left untouched and a new file is produced.

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?

Four short sentences, front-loaded with the core action and placement geometry, followed by the background-removal behavior, the textual-mark option, and the non-cryptographic caveat. No sentence is redundant and nothing important is buried.

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 12-parameter tool with no output schema, the description plus a fully annotated schema covers the essentials an agent needs to invoke it correctly. The remaining gap is outcome semantics (whether a new file is always created, what the result object contains), which matters given the readOnly annotation.

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 every parameter is already documented; the description's contribution is limited to reinforcing the coordinate origin ('as it is shown (rotated pages are handled)') and the image/width relationship. Useful, but the schema already carries the per-parameter detail (texts, threshold, pages, returnBase64), so this stays at the high-coverage baseline plus a small increment.

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 ('Place a signature ... image on PDF pages') plus the placement model (x/y/width in points from the top-left). It also rules out the most likely confusion by saying 'This is a visual signature, not a cryptographic digital signature', which separates it from signing/verification tools and from pdf_form_fill.

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?

Gives clear context for when this is the right tool (stamping an image of a signature, initials, stamp or logo) and names an alternative path for handwritten drawing via the web link. It does not explicitly contrast with nearby siblings such as pdf_watermark (image placement) or pdf_form_fill (signature fields), leaving that inference to the agent.

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