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

Goes well beyond the readOnly/openWorld annotations by disclosing the full return shape, deterministic SHA-256 ids, the billing model (2 credits per successful call), and the key guarantee that schema-invalid input is rejected before billing. That billing-before-validation detail is exactly the kind of behavior an agent cannot get from structured fields.

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 capability, then gives a compact return-shape and pricing statement with zero filler. Slightly dense in the second sentence, but every clause carries information.

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?

For a 5-parameter, no-output-schema tool, the description covers the output object, determinism, cost, and validation behavior. An agent has everything needed to call it and anticipate the response.

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 the schema already explains modes, size range, tokenizer families, and the 'overlap under half of size' constraint. The description restates the mode options and overlap but adds no format or interaction detail the schema lacks, so baseline 3 applies.

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 plus resource ('Splits text for retrieval') and enumerates the three strategies (tokens, sentences, markdown headings) along with overlap and stable SHA-256 ids. This clearly separates it from counting tools like token-count or text-stats, which measure rather than segment.

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 phrase 'for retrieval' implies the RAG use case, but the description never says when to pick this over siblings such as token-count, dataset-split, or page-markdown, nor does it state exclusions. Usage is inferable but not directed.

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