PowerPlatform MCP

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 successfully notes that original trigger inputs are reused, but fails to disclose whether this creates a new run ID, overwrites existing data, requires specific auth scopes, or has rate limiting implications.

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, front-loaded sentence of nine words with zero redundancy. Every word earns its place by conveying the action, target state, and execution mechanism.

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?

Given the presence of an output schema, the description appropriately omits return value details. However, for a mutation operation with zero annotations, it should disclose safety characteristics (idempotency, destructive potential) which are absent.

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%, establishing a baseline of 3. The description adds minimal parameter-specific context beyond the schema, though 'using the original trigger inputs' implicitly clarifies that runId refers to the failed execution whose inputs will be reused.

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 identifies the action (resubmit/retry), target resource (failed flow run), and key mechanism (original trigger inputs). However, it doesn't explicitly distinguish this from sibling 'cancel-flow-run' or clarify whether 'resubmit' and 'retry' are distinct operations.

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 implies usage by specifying 'failed flow run,' suggesting it should only be used on failed executions. However, it lacks explicit when-to-use guidance, prerequisites (e.g., required permissions), or comparison to alternatives like cancel-flow-run.

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