For 'I know the topic but not the citation': the titles, chapters, articles, and parts whose headings carry the words, with the code_browse call that lists each.
| Name | Required | Description | Default |
|---|---|---|---|
| words | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool searches headings specifically, which is a behavioral detail beyond the readOnlyHint and idempotentHint annotations. It also implies a return format that includes the code_browse call, but it does not explain pagination, limit, or exact matching behavior. Since annotations already cover the read-only and idempotent nature, the description adds useful but limited context.
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 a single sentence that front-loads the use case and then specifies the search target and result. It is concise with no filler, though the final clause 'with the code_browse call that lists each' adds a slight ambiguity and could be simplified. Overall it is well-structured and efficient.
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?
For a tool with a single parameter and no output schema, the description covers the core purpose and use case, and differentiates from siblings by emphasizing heading searches. However, it lacks details about the output format (other than mentioning code_browse), edge cases, or any limitations, leaving the agent to guess about response structure and exact behavior. It is adequate for a simple tool but not exhaustive.
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?
With 0% schema description coverage, the description must clarify the single 'words' parameter. It states that headings 'carry the words', indicating that the parameter is a string of terms to match against headings. This gives basic meaning but omits details like case sensitivity, whether it's a phrase or individual words, and how multiple terms are handled. It is better than nothing but not comprehensive.
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 clearly states the tool finds titles, chapters, articles, and parts whose headings contain the given words, and that it pairs each with a code_browse call. It is specific about the resource type (legal code components) and the search scope (headings), which differentiates it from siblings like code_search that might search full text. The phrasing is somewhat awkward but the purpose is unambiguous.
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 opening 'For I know the topic but not the citation' provides a clear use case, indicating when to use this tool: when the user has a topic but lacks a citation. However, it does not explicitly mention alternative tools or when not to use it, leaving the choice of sibling tools like code_search or code_find_act to the agent's inference. It gives context but no exclusions or comparisons.
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.
Each tool has a unique and clearly defined purpose, separated by collection (bills, code, opinions, constitution) and action (list, lookup, search, get_text, browse, etc.). No two tools overlap in functionality.
Tool names follow a consistent pattern of collection_action (e.g., bills_list, code_search, opinions_lookup) with snake_case and descriptive verbs. General tools use clear single-word names like search, fetch, and verify_quote.
With 23 tools, the set is slightly larger than the typical 3โ15 range, but it is appropriate for a comprehensive legal database covering multiple collections and specialized operations (browse, describe, find, verify). The count is justified by the domain's breadth.
The tool set covers all major legal collections (bills, code, constitution, opinions) with CRUD-like operations (list, lookup, search, get_text) and includes cross-cutting utilities (search, fetch, verify_quote, describe_site, get_coverage). No obvious gaps in the expected functionality.