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

With no annotations supplied, the description carries the full behavioral burden and does much of it: it discloses that long sections are split into parts, that a TRUNCATED marker signals incomplete text, and that offset is the resumption mechanism. It also flags provenance ("where it came from") and explicitly frames output as reference text, not a verdict. It says nothing about permissions, rate limits, or error behavior, keeping it off a 5.

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 operational content is tight and the mode logic is clearly staged, but the actual purpose appears only after four sentences of product-level legal disclaimers ("Not for clinical use", synthetic test data only, no patient care decisions). Necessary compliance text, yet it delays the front-loaded answer an agent needs, and the trailing "not clinical advice" repeats an earlier warning.

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 three-parameter read tool with a declared output schema, the description covers the essentials: what each mode returns, how to resume truncated reads, and what the output is not. The main omission is any guidance on the surrounding workflow (how to obtain the document_id in the first place, or when a monograph is preferable to an FDA label).

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 compensate and largely does: document_id is characterized as a document number whose sole presence switches the tool into section-listing mode, section is characterized with a concrete reference format (M013.50), and offset is tied causally to the TRUNCATED reply. The only gap is that offset's unit (characters/blocks) and the section-reference grammar are not fully specified.

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?

"Read FDA OTC monograph text" names a specific verb and resource, and the description then spells out the two distinct modes: with only a document number it lists sections, with a section reference like M013.50 it returns that section's text plus provenance. That dual-mode explanation lets an agent distinguish it from siblings such as read_fda_label_section or get_otc_monograph without opening a 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?

The description gives solid in-tool guidance for its own modes and even prescribes recovery behavior when a reply says TRUNCATED (call again with the offset before relying on the text). However, it never states when to choose this tool over the closely named siblings find_otc_monographs, get_otc_monograph, or read_fda_label_section, so routing between monograph tools is left to inference.

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