Check legal citations in text

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

Beyond the annotations (readOnly, idempotent), the description discloses the return format (coverage statement, counts per tier, rows per tier, report id), the semantics of red/orange rows, the fact that deep mode sends clauses to a model judge, and rate limits (free tier 20/month, deep 3/month). This goes well beyond the annotations and gives the agent a clear behavioral model.

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?

The description is dense but front-loaded: purpose in the first sentence, usage in the second, then returns, limitations, result interpretation, deep mode, and limits. Each sentence adds distinct information with no redundancy, though it is long. It could be trimmed slightly, but the detail is mostly necessary for correct use.

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 specifies what the tool returns (coverage statement, counts per tier, one line per row needing human, number of citations, report id) and how to interpret red/orange rows. It also covers limitations, deep mode, and rate limits, making it complete for an agent to invoke 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 100%, so parameters are already documented. The description adds context for deep=true: it generates white rows, takes 1-2 s per citation, sends clauses to a model judge, and produces a review queue, not a verdict. For text, it repeats the schema's 'paragraphs, footnotes, a whole brief' but adds context about draft briefs and memos; the added value is moderate but meaningful.

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: 'Check every case citation in a text against proofread.law's register of about 10 million US court opinions (CourtListener bulk data).' It also lists what the tool cannot do ('Cannot: resolve Westlaw (WL) or Lexis identifiers, check statutes, regulations or secondary sources...'), which clearly distinguishes it from sibling resolve_citation(s) and check_document tools.

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 explicitly says when to use it: 'Use it on a draft brief, memo, letter or any prose that cites cases, before the citations are relied on.' It also states exclusions via the 'Cannot' list, and describes deep=true as an optional mode, so an agent knows when not to enable it. The interpretation guidance for red/orange rows further clarifies usage.

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