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

Annotations already declare readOnlyHint=true, openWorldHint=false, destructiveHint=false, so the safe-read profile is covered. The description adds substantial behavior beyond that: the default mode behavior, what an operationId response includes (inputs, outputs, dynamic parameter metadata, nextTool hints, authored hint + canonical example), variant selection behavior when omitted, and cross-connector suggestion semantics.

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 about 150 words and front-loads the core purpose in the first sentence. Every subsequent sentence adds new information—mode semantics, operationId expansion, variant hints, and the full-mode exclusion. There is no repetition of schema content and no filler.

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 9-parameter tool with no output schema, the description is notably complete: it covers the two modes, the cross-connector search path, variant dispatch, and the downstream tool hints. Minor gaps remain: it does not explicitly describe the shape of the returned operation catalog/search results, nor the interaction between mode=full and operationId, but these are minor given the rich schema and known sibling context.

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 100%, so the baseline is 3. However, the description enriches operationId beyond the schema—it not only says 'expanded inputs and outputs' but also mentions dynamic parameter metadata and the nextTool/hint integration. It also clarifies the search/connectorName relationship ('Use search without connectorName/apiName to search operations across connectors') beyond what's in the schema.

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 pairing: 'Describe a live Power Platform connector/API and its operations.' It clearly differentiates the tool from siblings such as get_live_flow (flow-level details), get_live_dynamic_options (dynamic option resolution), and update_live_flow (flow editing). The reference to Canvas MCP describe_api also pins down the intent distinctly among the many sibling introspection tools.

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 gives explicit routing: use mode=summary by default for a compact catalog, use operationId to get one operation with expanded details, use search without connectorName/apiName to search across connectors, and a clear exclusion—'Use mode=full only when raw OpenAPI connector metadata is required.' It also names the next hop tool (get_live_dynamic_options) and mentions the output shape going into update_live_flow.

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