Get Running Requests

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered; the description adds real value on top by disclosing the returned field set (including blocking session and open transactions) and the semantic effect of includeSleeping. It stops short of noting that DMV snapshots can be costly under load or that results are point-in-time only (no history), which would push it higher for an observability tool.

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 tight sentences with the core purpose front-loaded and no filler; the field enumeration is dense but earns its place since no output schema exists. Slightly list-heavy, which costs it the top mark, but nothing is wasted.

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?

With no output schema, the description competently shoulders the burden of describing the return contents, and it resolves the one parameter plus the sibling overlap. It omits scope details (instance-wide vs. current database) and any note about snapshot/latency behavior, which are the remaining gaps for full completeness.

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 100% and the single boolean is already documented in the schema with the same meaning; the description restates includeSleeping without adding format or edge-case detail. Baseline 3 is correct when the schema carries the parameter semantics.

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?

States a specific verb+resource ('Running requests now: active user sessions') and enumerates exactly what each row contains (status, command, CPU, reads, elapsed time, wait type, blocking session, open transactions, current statement). It explicitly distinguishes itself from the sibling mssql_blocking for the blocked-only case, so an agent can route without opening either schema.

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?

Names the alternative (mssql_blocking) together with the condition that selects it ('For blocked sessions only'), and gives the condition that changes this tool's own behavior ('includeSleeping=true also lists idle sessions that hold an open transaction'). Nothing essential is left to inference.

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