generate_pdf

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

Annotations provide no behavioral hints beyond readOnlyHint:false and destructiveHint:false, so the description carries the burden. It discloses the conversion method (headless-browser HTML-to-PDF) and the return mechanism (base64 embedded plus downloadUrl over httpStream), which is valuable. It does not mention any side effects or limitations, but the core behavior is transparent and consistent with annotations.

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 two sentences, front-loaded with the purpose and output details. It avoids redundancy and includes only essential information: what it does, how it does it, and how results are returned. No wasted words, and the structure is logical (action, features, delivery).

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 adequately explains the return value (base64 PDF plus downloadUrl). It also references generate_report's schema for the input structure, which is necessary for correct invocation. It lacks details on error handling or edge cases, but for a rendering tool that relies on a well-defined input schema, it is sufficiently complete for an agent to call it correctly.

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 50% with some parameters documented (tags, brandName, preparedBy, brandTagline, classification). The description adds context by pointing to generate_report's schema for the 'sections' parameter, which helps agents understand the required structure. However, it does not describe the remaining parameters (title, subtitle, companyName, generatedAt) beyond what the schema provides, so it adds limited value for those.

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 states a specific action: renders a structured report into an institutional-layout PDF with enumerated features (cover page, TOC, headers, footers, page numbers, tables, per-section confidence, citations). It clearly distinguishes from sibling tools like generate_report (which produces the structured data) and generate_markdown (a different output format). The verb 'Renders' plus the output specification make the purpose unambiguous.

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 explicitly says the input is a structured report from generate_report, indicating this tool is intended to be used after that. It also notes the PDF is returned as a base64 resource for remote clients, implying a specific delivery context. However, it does not explicitly mention alternatives such as generate_institutional_report or generate_markdown, nor when to choose one over the other, leaving some ambiguity among sibling tools.

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