Strata session autonomy

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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine value beyond this by disclosing that the autonomy level is the user's, set out-of-band (Agents page or the MCP's own env) and never mutable by an agent — context about governance and modification authority that annotations cannot convey. It also enumerates the level values (ask / limits / instant), enriching the behavioral model.

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?

Two sentences, zero waste. The first sentence front-loads the purpose with a concrete verb and enumerates exactly what's returned; the second sentence adds a critical behavioral constraint. Every clause earns its place, with no redundancy against the annotations.

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?

Although there is no output schema, the description covers the essential surface: the return contents (level enum values, ceilings, change instructions) and the read-only nature. For a simple 0-parameter read tool with strong annotations, this is nearly complete — it could marginally benefit from describing the exact response structure, but the description suffices for an agent to know what to expect.

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?

With 0 parameters, the baseline is 4 per the rubric. The description does not discuss parameters (correctly, since there are none) but instead describes the semantic output: the autonomy level with its three possible values, USD ceilings, and how to change the level. This is the appropriate use of description space for a no-parameter configuration read.

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 uses a specific verb ('Read') with a clear resource (autonomy level, USD ceilings), and states exactly what information is returned (level values ask/limits/instant, ceilings, change instructions). It clearly distinguishes itself from all sibling tools, which deal with capabilities, status, execution, or market data — none of which cover the session autonomy configuration.

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 opening phrase 'Read how much this MCP may finish by itself' gives clear context for when to call this tool (when the agent needs to understand its autonomy ceiling and spending limits). The read-only caveat with 'never by an agent' effectively tells the agent this is a query-only operation, though it never names an explicit alternative tool for changing settings (since none exists — that's done out-of-band).

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