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

Annotations already cover readOnly/idempotent/openWorld, but the description adds substantial behavioral context beyond them: a hard point-in-time freeze (2021-05-21, release 76), why the current code is unreachable (LexisNexis wall), explicit current_through labelling, and the later_acts overlay with sessions_checked semantics. This is far more than the annotations disclose.

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?

Core purpose and the critical point-in-time caveat are front-loaded, and most sentences carry operational weight. Some content (litigation references, README pointers, the lengthy explanation of the home-built index) is denser than selection requires, slightly hurting scannability.

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 fully compensates by enumerating return contents (statutory text, catchline, chapter context, Acts history, current_through, later_acts, sessions_checked) and stating coverage of all 68 titles. Nothing an agent needs 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 schema already documents the citation format, but the description adds genuinely new meaning: acceptance of natural citation forms ('T.C.A. 39-13-202', 'Tenn. Code Ann. § 39-13-202') and the title-is-before-first-dash anatomy. Useful above the baseline of 3, though partly overlapping the schema example.

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 ('Get a section of the Tennessee Code Annotated... by citation') and immediately grounds it with concrete example citations. An agent can distinguish it from the sibling tn_search (search) without opening either 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?

Gives explicit use cases ('what does T.C.A. 39-13-202 say', 'check a Tennessee statute AND whether it has been amended since 2021-05-21') and an explicit when-not ('NOT case-law digest... which this pack excludes'). The snapshot-frozen nature defines a crucial usage boundary.

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