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

The readOnlyHint/destructiveHint/idempotentHint annotations already establish the safety profile and the description is consistent with them, then adds behavior the annotations cannot express: no file is produced, the 15 MB size cap, the 50-page search limit, and the failure mode for image-only PDFs with the fallback path. These are precisely the operational constraints an agent needs before calling.

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?

Content is front-loaded: use case first, then what it returns, then limits, then exclusions. Every clause carries information, though the single dense block could be split for faster scanning and the return-field enumeration is slightly buried mid-sentence.

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 one-parameter read tool with an output schema, the description still goes beyond the minimum by describing the returned fields (page, x, y in points from top-left as displayed, width, spot id) so the agent understands how results chain into sign_pdf. Limits and the scanned-PDF gap close the remaining blind spots.

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?

There is a single required parameter and the nested schema documents every field at 100% coverage, so the schema carries the semantics. The description adds only marginal framing by calling it "the PDF to look in" and naming the size limit, which is useful but largely redundant with the schema.

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 opens with a concrete verb and resource — locating signature, initials, date and name spots in a PDF — and enumerates exactly which patterns it detects (labels, blank ____ lines, empty signature form fields). That makes it unambiguously distinct from the sibling sign_pdf, which performs the actual signing.

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?

It gives positive triggers (user wants to sign, fill a signature line, find where to sign, add initials or a date), an explicit exclusion ("Do not use for reading or summarizing a contract"), and a named alternative with instructions (give page and position to sign_pdf for scanned PDFs without a text layer). Nothing about tool selection is left to inference.

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