deny_permission

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

With no annotations provided, the description carries the full burden. It discloses that the tool executes a SQL DENY command, lists preconditions (blocked by readonly), and provides constraints on parameters (e.g., columns only for OBJECT scope with specific permissions, empty list raises error). It could be improved by noting return value or idempotency.

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 well-structured with a brief intro followed by a parameter list. The parameter descriptions are concise but comprehensive. Minor repetition could be trimmed, but overall it is efficient and front-loaded.

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 8 parameters, 4 required, and no schema descriptions, the description covers all necessary information for usage, including constraints and examples. It does not describe the output schema, but that exists separately. Overall, it is complete enough for an AI agent to invoke correctly.

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%, so the description must add meaning. It does so thoroughly, explaining each parameter's purpose, default values, required conditions, and constraints (e.g., schema required when scope is SCHEMA, columns limited to certain permissions). This far exceeds what the schema alone provides.

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 the action ('Deny permissions') and the target ('securable to a principal'), and provides the SQL equivalent. This is a specific verb-resource pair that distinguishes it from siblings like grant_permission and revoke_permission.

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 mentions that the tool is blocked by FABRIC_MCP_READONLY and does not require FABRIC_MCP_ALLOW_DESTRUCTIVE, providing some behavioral context. However, it does not explicitly guide when to use deny vs. grant/revoke, nor does it mention prerequisites like having appropriate permissions to execute the denial.

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