Cross-link a UI facility to the program(s) that implement it — 'what code runs this screen?'. Each program carries a match label: declared (named by the facility's menu entry, authoritative) or titleId (TITLE id equals the facility code). Complements lookup_facility (which gives the facility's tables and call graph). Metadata only — no source body.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | Facility code, e.g. AP_A_002 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states 'Metadata only — no source body,' setting expectations that no code is returned. It also explains the two match labels (declared vs titleId), which is useful behavioral context about the output semantics. This is strong but not exhaustive; it doesn't mention error behaviors or pagination, though these are less critical for a simple metadata lookup.
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 concise—two meaningful sentences plus a clarifying phrase. It front-loads the main purpose, then adds essential details about output labels and relationship to a sibling tool. Every sentence contributes value; no filler or repetition.
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, this description is remarkably complete. It explains what the tool does, what the output looks like (programs with match labels), what the labels mean, the metadata-only limitation, and how it fits with lookup_facility. Given the tool's simplicity, there are no significant gaps.
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?
There is one parameter (code), and the schema already provides 100% coverage with a description and example. The tool description refers to 'a UI facility' and uses 'facility code' implicitly, but it adds no additional meaning beyond what the schema already gives. Per the baseline rule, a score of 3 is appropriate when schema coverage is high and the description doesn't enhance parameter understanding.
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 opens with a specific verb+resource: 'Cross-link a UI facility to the program(s) that implement it' and clarifies the core question: 'what code runs this screen?'. It also distinguishes itself from sibling lookup_facility by explicitly stating that this tool gives programs while lookup_facility gives tables and call graph, so 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 description clearly positions the tool relative to lookup_facility: 'Complements lookup_facility (which gives the facility's tables and call graph).' This tells the agent when to use this tool vs that sibling. However, it does not explicitly compare to other siblings like program_facilities or table_programs, so the guidance is good but not exhaustive.
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 clearly distinct purpose: list/lookup/search pairs are separated by summary vs full detail, exact match vs fuzzy search, and domain scope. Cross-reference tools are explicitly paired as reverse lookups (facility_programs/program_facilities, table_facilities/table_programs), eliminating ambiguity. Minor overlaps like find_column vs search_columns and get_ddl vs lookup_table are well-differentiated by their descriptions.
The naming is largely predictable with list_ for browsing, lookup_ for full detail, search_ for searching, and _stats for overviews. Cross-links follow a noun_noun pattern (facility_programs, table_facilities). Exceptions like find_column, get_ddl, graph_neighbors, and path_between are still intuitive and do not create confusion, though they deviate from the dominant verb-first pattern.
At 21 tools, the set sits in the 16-25 range that feels heavy. However, each tool serves a distinct function across schema, facilities, programs, columns, and graph traversal, so the count is justified for a comprehensive data dictionary. It is not as tightly scoped as a typical CRUD server, but the breadth is necessary for the domain.
The tool set provides complete coverage for a read-only data dictionary: browsing, searching, full details, and cross-references for every entity type (objects, columns, facilities, programs), plus graph utilities. There are no obvious dead ends or missing operations; stats and search-all tools further enhance orientation and cross-domain discovery.