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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description need not restate them. It adds genuinely useful behavior beyond the annotations: the block 'collects no answer' and files are added elsewhere, preventing a misinterpretation of the write operation. It stops short of covering insert semantics like chaining/ordering, hence 4.

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?

Two tight sentences, front-loaded with the action and resource, with zero filler. The 'not here' caveat earns its place by preventing a wrong assumption about file loading.

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, annotations carrying the safety profile, and a fully documented parameter schema, the description covers the non-obvious essentials: what the block is and what it does not do. A brief note on insertion ordering would round it out, but nothing critical 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 description coverage is 100%, and the schema already explains the tricky interactions (after vs. position, $prev chaining, parentId scoping). The description adds no parameter-level detail and none is needed. Baseline 3 is appropriate.

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 the specific verb+resource ('Insert a Documents block') and immediately defines the resource: 'a download list of files (PDF, images) the owner hands to the respondent.' The clause 'Collects no answer' distinguishes it from sibling tools like editor_insertFileQuestion, so an agent can tell them apart without opening either schema.

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 a clear scope boundary — 'files are added in the editor, not here' — telling the agent that this tool only places the block and does not populate it. It also conveys the use-case (a non-answering download list) versus answering question blocks. However, it does not explicitly name the alternative tool or state exclusion conditions, so a 4 rather than 5.

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