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

Goes well beyond annotations by disclosing that sources are read-only and never modified, that the output is returned inline as an application/pdf resource, that only whole documents are concatenated, and that failures abort rather than yield a partial merge. Consistent with readOnlyHint=false (it produces a new artifact) with no contradiction.

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?

Front-loads the core action and return type, then scopes limits and alternatives. Every sentence carries distinct information with no filler.

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?

An output schema exists so return details are optional, yet the description still confirms the inline resource form and error behavior. For a one-param merge tool with sibling alternatives, nothing needed to call it correctly is missing.

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 100% and there is a single param, so the schema already defines the accepted URI forms. The description still adds value by emphasizing 'in the order given', clarifying that array ordering is semantically significant.

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 (merge PDFs into one, in order given) plus the return form. It distinguishes itself from siblings by naming pdf_fill and pdf_invoice as the tools for non-concatenation tasks.

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?

Explicitly scopes when to use this vs alternatives: only whole-document concatenation, no reorder/rotate/delete, and names pdf_fill and pdf_invoice with the conditions that select them. Includes the negative case (unreadable input fails).

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