get_clause_frequencyReturns how many of the 510 public commercial contracts in the CUAD v1 dataset contain a clause type, as counted for the FixMyContract /data/cuad page. Without an argument, returns every clause category, most common first.
| Name | Required | Description | Default |
|---|---|---|---|
| clause | No | Optional clause type or CUAD category name, e.g. "cap on liability". |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only/idempotent/non-destructive, so the bar is lower; the description still adds useful context: the exact dataset (510 CUAD v1 contracts), the provenance caveat ('as counted for the FixMyContract /data/cuad page'), and the default ordering when no clause is supplied.
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?
Two sentences, zero filler, and the core behavior (what is counted) is front-loaded before the default-case behavior. Nothing extraneous.
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 carries the return-value burden and does so adequately by describing counts per clause type and the ordering of the all-categories case. It stops short of confirming the exact shape (single count vs. name/count pairs), which is the only remaining gap for a one-parameter read tool.
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 it already documents the optional clause name, so the baseline is 3; the description goes one step further by defining what happens when the parameter is omitted (all categories returned, most common first), which the schema does not state.
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: it returns counts of contracts containing a clause type, over a named 510-contract CUAD v1 dataset. The purpose is concrete and clearly not the same as list_clause_types or explain_clause_type, though it never names those siblings to sharpen the contrast.
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 explains the no-argument path (return every clause category, most common first), which is genuine usage information, but gives no explicit when-to-use guidance or routing away from list_clause_types/explain_clause_type when the agent wants names versus counts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.