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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description still adds real behavioral value by disclosing that CAS numbers get check-digit verification and that output is evaluated against a specific regulation (Appendix D). What it omits is failure behavior — what happens with non-SDS text, partial sheets, or unparseable sections — and whether the label build is always emitted or conditional.

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?

A single front-loaded sentence with the main verb first, using semicolons to chain the three capabilities — dense but zero filler. The long enumeration of extracted fields is justified because it doubles as the return-value specification in the absence of an output schema. Slightly heavier than ideal for one sentence but nothing is wasted.

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, the description carries the burden of describing returns, and it does so by naming the exact fields extracted plus the regulation checked and the label artifact. Gaps remain around result shape (one object vs. separate parse/check/label sections) and error handling for malformed input, but for a one-parameter read-only tool this is close to sufficient.

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?

There is a single required parameter with 100% schema description coverage, so the schema already tells the agent to supply SDS text. The description reinforces that the text must be a GHS safety data sheet, which is mild added meaning. It gives no format hints (length, plain text vs. markdown, whether tables survive) that would help an agent prepare the argument.

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 opens with a specific verb+resource ('Parse the text of a GHS safety data sheet') and enumerates the extracted fields (signal word, pictograms, CAS-verified ingredients, exposure limits, flash point, PPE, revision date) plus two downstream actions: checking against 29 CFR 1910.1200 Appendix D and building a workplace label. No sibling tool covers SDS parsing or HazCom Appendix D, so an agent can route here without ambiguity. It falls short of 5 only because the multi-function nature (parse + compliance check + label generation) is not framed as a single coherent capability.

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?

Usage is implied by the input ('the text of a GHS safety data sheet'), so an agent knows this is the tool for SDS text. However, there is no explicit when-to-use statement, no guidance on what input is acceptable (raw PDF-extracted text vs. OCR noise), and no mention of when the compliance-check or label-building portions matter versus a plain parse. Neighboring OSHA tools are never referenced as alternatives or complements.

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