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

With no annotations, the description carries the behavioral burden and does disclose a real trait: the text is verbatim and unaltered, with no model paraphrasing, and it matches only the article's own wording (failure mode for loose queries). It does not state that the operation is read-only, mention permissions, pagination, or empty-result behavior, but the read-only nature is strongly implied by 'Return' plus citation framing.

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?

Purpose and output shape are front-loaded, then parameters, then the verbatim caveat and alternative routing. Nearly every sentence earns its place, though 'word for word' and 'verbatim and unaltered' restate the same guarantee, making the middle slightly denser than needed.

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?

An output schema exists, so return values need not be spelled out, and the three parameters are each explained despite 0% schema coverage. Coverage is near-complete for a retrieval tool; only edge behavior (no matches, article not found) is unaddressed.

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 0%, so the description must compensate, and it does for all three parameters: 'query' is the distinctive words asked about (with examples of what counts), 'article' is optional and accepts an @id, page url, or title, and 'limit' is bounded to 1-5 with a default of 3. This adds meaning the bare schema types do not.

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 and resource ('Return passages of the VISEON articles word for word') and immediately defines what each passage carries (link, article, query coverage) and why (so an answer can quote and cite). It also distinguishes itself from retrieval-of-graph-metadata siblings by naming them. An agent can tell what this tool produces without opening the 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?

It gives a clear routing rule: use this for verbatim article text, and use fuzzy_find_and_traverse / get_entity 'for what the graph says about an article.' It also advises phrasing the query 'in the words the article would use.' The gap is the overlapping sibling search_content, which is never mentioned or differentiated, and no explicit when-not condition beyond graph metadata.

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