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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the bar is lower, yet the description still adds real value: keyless access (no auth setup), what is returned (current text, catchline, chapter/subchapter context, amendment-history chain), and the explicit limitation that Delaware publishes current text only with no per-year archive and the tool refuses to guess. Missing only edge behavior such as what happens on an invalid or nonexistent citation.

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-loaded with the core action and kept dense rather than padded, with examples doing real work. Minor waste exists in echoing the same two citations twice (once in prose, once implicitly in the schema examples) and in the one-word "Keyless." fragment.

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 single-parameter, annotated, no-output-schema tool this is complete: it covers accepted input forms, what the response contains, the absence of historical versions, and the lack of auth requirements. Nothing an agent needs in order to call it correctly is missing.

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 baseline would be 3, but the description goes beyond the schema by listing accepted natural citation forms ("11 Del. C. § 636", "Title 11 § 636") that the schema does not mention, plus letter-suffix sections. This meaningfully reduces the chance of the agent rejecting or mangling a valid citation format.

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 and resource — retrieve the full text of a Delaware Code section by citation — and makes it concrete with two worked examples (11-636 murder, 6-2734 automatic renewal). An agent can immediately tell this is a citation-lookup tool. It never names the sibling `de_search`, so the distinction from keyword-style searching is implied by "by citation" rather than stated.

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?

Gives concrete when-to-use triggers ("what does 11 Del. C. 636 say", checking a statute a case or lease relies on) and an implicit when-not in noting that only current text exists, so historical-version requests should not be routed here. It stops short of explicitly directing the agent to an alternative such as `de_search` when no citation is in hand.

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