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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds some context by revealing that comparison uses summaries and key chunk excerpts, but it does not disclose the return format, whether output is a generated narrative, or how chunk selection works. OpenWorldHint=false also provides context, but behavioral transparency beyond that is minimal.

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 a single, front-loaded sentence with no filler. It communicates the action, object, and mechanism efficiently, earning its place fully with zero redundancy.

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 and only a terse description, the definition lacks clarity on what the tool returns (e.g., a summary of similarities/differences, a list of excerpts) and how the result should be interpreted. It also omits guidance on prerequisite setup, such as how to obtain document IDs. The description is not sufficient for a 3-parameter tool with no structured return documentation.

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 0%, so the description must carry meaning. It maps document_id_1 and document_id_2 to 'two documents' and links excerpt_chunks to 'key chunk excerpts,' which gives an agent a rough semantic understanding. However, it doesn't explain the exact role of excerpt_chunks (e.g., number of chunks per document or total) or any constraints on IDs, leaving notable ambiguity.

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 verb ('Compare'), a clear resource ('two documents'), and the method ('using summaries and key chunk excerpts'). It clearly differentiates from all sibling tools, none of which perform document comparison, and leaves no ambiguity about the tool's core function.

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 implies a use case (comparing two documents) but gives no explicit guidance on when to choose this tool over alternatives like semantic_search or summarize_document. There are no exclusions, prerequisites, or conditions stated, so an agent is left to infer usage from the name and verb alone.

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