ise_mnt_request

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

No annotations are provided, so the description carries the full burden. It flags '[DESTRUCTIVE]' in the description itself, discloses that the server requires an operator to enable destructive tools (CISCO_ISE_MCP_ALLOW_DESTRUCTIVE=1), and notes it 'Returns raw XML.' However, it could further clarify what operations are destructive vs. read-only (e.g., a GET passthrough vs. a DELETE), though the confirm-flag mechanism partially covers this.

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?

Three sentences, zero waste, front-loaded with the critical DESTRUCTIVE warning and primary purpose. Every sentence earns its place: what it does, an example, and the legacy alternative guidance.

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 raw passthrough tool with 5 params and high schema coverage, the description provides complete guidance. It covers the destructive nature, the confirmation mechanism, the deployment targeting, and the reporting alternative. The absence of an output schema is partially mitigated by 'Returns raw XML.' Given its passthrough nature and rich schema, this is 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 coverage is 80% (high), so baseline is 3. The description adds value beyond the schema by explaining the confirm parameter's destructive requirement and dual-layer enforcement (tool-level confirm plus environment variable). It also clarifies deployment param semantics (name/slug/number, omit for default, reference to ise_list_deployments). The params param and method enum benefit from the high schema coverage.

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 states a specific verb+resource: 'Raw Monitoring (MnT) passthrough — call ANY /admin/API/mnt/ endpoint not covered by a typed tool.' It provides an example endpoint and explicitly distinguishes it from typed tools (ise_mnt_*, ise_dc_*) that already cover specific endpoints, making selection 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?

Explicitly states when to use: 'call ANY /admin/API/mnt/ endpoint not covered by a typed tool'. It also gives a clear exclusion and alternative: 'MnT is legacy; prefer Data Connect (ise_dc_*) for reporting.' This distinguishes it from the many typed ise_mnt_* and ise_dc_* sibling tools.

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