rag_lookup_object

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, and it largely meets it. It openly reveals a real limitation (configuration-only view of an indexed snapshot, not live data) and a diagnostic caveat (absent objects may simply be unindexed; check rag_diagnostic first). It does not, however, disclose return format or pagination, and it does not explain what 'indexed' means operationally — small gaps, but the honesty about scope earns credit.

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 tight — the primary purpose is stated in the first sentence and the boundaries are compressed into a compact second paragraph. The paragraph break and dashes keep the caveats readable. It loses a point because the two-sentence purpose block could be trimmed slightly (e.g., 'RAG describes...' could be a single clause), but nothing is wasteful.

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?

The purpose and scope are well covered, and the presence of an output schema means the return shape need not be described. But the total silence on the parameters is a genuine completeness gap for a three-parameter tool, and the relationship to the sibling session/index lifecycle (rag_session_autoconfigure, rag_snapshot_create) is only implied. This is above average but not fully complete.

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 description coverage is 0% and the description adds nothing about the three parameters. There is no guidance on what 'object' should contain (a name? a path? a GUID?), what 'snapshot' selects, or how 'session_id' ties into sessions_list / rag_session_autoconfigure. For a tool whose core payload is the 'object' parameter, omitting any format or syntax hint forces the agent to guess.

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 pair ('Look up an indexed 1C metadata object'), immediately names the payload ('navigation, fields and forms'), and sharpens scope by stating what RAG describes ('configuration source metadata'). This distinguishes it cleanly from the UI-interaction and live-state siblings such as rag_query, find_object and get_object without needing to open a schema.

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 second sentence explicitly demarcates what RAG does NOT cover — live infobase data, access rights, user settings, and report results — and then hands the agent a decision rule: inspect rag_diagnostic before concluding an object is absent, and switch to live UI tools when current runtime state matters. That is explicit when/when-not guidance with concrete alternatives named.

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