ecp_mssql_revoke_privileges

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

With no annotations, the description carries the behavioral weight. It helpfully discloses that the operation is schema-wide (SCHEMA::dbo) and limited to 5 DML permissions, but it does not detail failure modes, whether the operation is idempotent, or whether the user/database must already exist. This is partial transparency: an agent knows more than the tool name, but still lacks some operational cues.

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 two sentences with no filler. The main action is stated first, and the second sentence adds a highly relevant limitation about privilege granularity. Everything present earns its place.

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?

The description addresses the most important non-obvious fact about MSSQL so good to see, but it does not cover what happens when the user or does not exist, whether revocation is silent or errors, or whether there are prerequisites beyond the confirm flag. The missing output schema and absence of annotations make these gaps more noticeable, though the schema makes the confirm boolean and enum values clear.

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 compensate for the schema's bare property names. It only provides a general 'user on database' framing and a note about schema-wide scope. It does not individually clarify db_name, db_username, privileges, or the confirm parameter beyond what the schema already provides via enum and const, leaving the agent to infer most parameter behavior.

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 states a specific verb ('Revoke'), a specific resource ('privileges from a user on a database'), and clearly scopes it to MSSQL. It also adds a distinguisher by explaining that MSSQL's model is coarse/schema-wide, which separates this from MySQL/PostgreSQL revoke tools and from sibling grant/list 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 strong context about when this tool is appropriate: for MSSQL databases and for revoking one of the listed 5 DML privileges. The note about being 'not per-table' provides an explicit exclusion, though it does not name sibling alternatives such as ecp_mssql_grant_privileges or ecp_mssql_list_privileges.

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