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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds non-obvious behavior beyond them: it parses multiple citation spellings and falls back to nearby sections when an id does not exist. That fuzzy-resolution behavior is exactly the kind of trait an agent could not infer from annotations.

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 sentence, front-loaded with the verb and resource, with examples placed immediately after the key noun. No filler sentences or restated title.

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?

Output schema exists so return values need not be enumerated, and the description still summarizes them; annotations cover the safety profile. The remaining gap is ambiguity handling — what is returned when text contains several citations or an unresolvable one, beyond the 'nearby sections' note.

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?

One required parameter with 0% schema description, so the description must carry meaning — and it does, giving three concrete example strings ('IC 31-16-15-25', 'I.C. § 7.1-1-1-1', 'Ind. Code § 35-42-1-1 (2024)') that define what 'text' accepts, including year-qualified forms. It does not say whether the whole text can be long or contain multiple citations.

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?

Specific verb+resource: 'Find Indiana Code citations in free text' with concrete examples of accepted formats and a stated return (canonical section ids, headings). It is clearly distinguishable in intent from id-fetching siblings such as ic_get_section, though it never names them explicitly.

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 examples imply the 'when' (you have unstructured text, not a known id), and the trailing clause hints at a fallback when an id does not resolve. But there is no explicit guidance like 'use this first, then ic_get_section with the returned id' nor any statement of when not to use it.

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