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

Beyond the readOnly/idempotent/closed-world annotations, it discloses that policies change without notice, that unposted policies are absent, that revoked policies are listed with a successor, that held numbers return only status/reason and never text, and that Hawaii serves machine-read text for only 40 of 204 files. These are exactly the behavioral caveats an agent cannot infer from annotations or schema.

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?

It is front-loaded correctly — purpose and the not-law boundary come first, caveats after — and nearly every sentence carries unique information. However it is a dense, run-on block with repeated constructions (multiple "answers X, never text" clauses) and partially duplicates the schema's "give number or query, not both" rule, which costs it readability.

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 carries the burden: it enumerates the returned fields (number, title, printed dates, replaced version, GLO read date, coverage_note) and explains the non-text outcomes for held, not-posted and revoked numbers. Coverage caveats for partial departments and Hawaii round out everything needed to call it correctly.

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 already 100%, so the baseline is 3, but the description adds real meaning: keyword matching does no stemming, the special number value "contents" lists a department's files, and number forms vary per department (Kansas General Orders such as "TCF 15-101", BOP "OP 038.1"). Only the limit parameter's behavior is left entirely to the schema.

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 first sentence names a specific resource (internal policies of a state DOC or the Federal BOP) and the two lookup modes (by number or by keyword query), and it explicitly carves out what it is not: statutes, regulations and court rules. That negative framing distinguishes it cleanly from siblings like statute, statute_search and citation without needing their schemas.

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 states a hard operational rule ("Give number or query, not both"), explains that a state absent from the enum simply isn't loaded, and routes the agent to sources(tool="corrections_policy", source=<code>) for per-department coverage and number forms. It stops short of explicitly naming which sibling to use when the target is actual law, though the "NOT law" framing implies it.

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