get_schema

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

With no annotations supplied, the description carries the whole load and does well on several axes: read-only framing ('without writes'), a 60s profiling cache with an explicit invalidation path, and 'unavailable fields carry explicit errors' signalling graceful degradation. It still omits permission requirements, response envelope, and how large a payload 'full' produces, which matters for a verbose model dump.

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?

Front-loaded with the read-only framing and tightly packed, but sentences run together into a near-run-on with typographic slips ('up to10 distinct samples', 'cached60s'). Information density is high and little is wasted, though bullet-style separation of the detail/refresh/page rules would improve scanability.

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 5-parameter tool with no annotations, no output schema and zero schema description coverage, the description supplies most of what an agent needs: return content, cache behaviour, default behaviour and the page/reportDir coupling. The residual gaps are connectionId semantics and the shape of the returned object.

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 0%, so the description must compensate and largely does: it defines the summary/full trade-off, the refresh/cache relationship, and explains that page requires an internal or display page name plus reportDir or a report-kind connection, adding meaning well beyond the bare schema types. connectionId is the one required parameter left unexplained, likely a deliberate assumption.

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?

Opens with a specific verb and resource: 'Read model context without writes', then enumerates what the read returns (DAX cardinality, BLANK share, min/max, distinct samples, hidden/key flags). The agent can tell this is a model-introspection tool, though it never names a sibling (list_pages, run_dax, connect_model) to sharpen the boundary.

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?

Gives explicit conditional guidance for two parameters: 'Default detail=summary omits measure DAX and relationship graph; ask for full to understand calculations and join paths' and 'use refresh after model/data changes.' No when-not guidance or comparisons to sibling tools, so the agent must infer the division of labour with list_pages/run_dax on its own.

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