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

With no annotations, the description carries the full burden. 'Atomic transaction' is a genuine behavioral disclosure (all-or-nothing, no partial output), but nothing is said about failure modes, whether the input document is mutated, or what the result looks like. The trailing sentences about prices, payment streams, and prepaid credits are irrelevant boilerplate that actively distracts rather than informs.

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?

Only the first sentence earns its place. The two sentences about retail prices, enabled payment streams, and legacy prepaid credits have no relationship to document cleaning or chunking and should be removed; they read as misfiled boilerplate.

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?

No output schema and no annotations mean the description must cover behavior and results, and it does not. With an undocumented second parameter and no explanation of chunk output shape or ordering, an agent cannot predict what it will receive.

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%: the 'document' parameter is well documented in the schema, but 'max_chunk_size' has no description anywhere. The description does not compensate at all — it says nothing about chunk sizing, its default of 1000, or what happens at the 16000 boundary.

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 opening sentence names a specific compound operation: cleaning markdown artifacts plus semantic chunking, performed atomically. 'Compound utility' implicitly signals that it wraps the two sibling tools clean_markdown and chunk_document, but it never names them, so differentiation is left to inference.

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?

There is no statement of when to use this composite tool instead of calling clean_markdown and chunk_document separately, nor any prerequisite or exclusion. 'Compound utility' hints at the combined case but gives the agent nothing actionable to route on.

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