get_capabilities

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it states the server only executes synthetic demo actions (not real-world actions), that the response distinguishes implemented actions from verified live execution, and that the tool 'does not change saved state.' This is meaningful behavioral disclosure that helps an agent trust the tool and interpret its output correctly.

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 compact and front-loaded with the most important usage directive. Each sentence adds distinct information: when to use, what is returned, server scope, response structure, and side-effect guarantee. It is slightly repetitive in places (e.g., 'synthetic demo actions only' and 'distinguishes implemented actions from verified live execution' both touch on the demo nature), but overall it is efficient and well-structured.

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 zero-parameter, read-only capability probe with an output schema present, the description is nearly complete. It covers when to call it, what it returns, the server's execution scope, and the no-side-effect guarantee. The only minor gap is that it doesn't explicitly describe the output schema structure, but the presence of an output schema means the description need not explain return values in detail. The mention of 'ESPN companion' and 'acceptance report' is slightly cryptic but not blocking.

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?

The tool has zero parameters, so there is no parameter semantics burden on the description. The schema coverage is 100% (vacuously, since there are no properties). The description instead explains what the response contains, which is the relevant semantic information for a no-arg capability probe. A baseline of 4 is appropriate for a zero-parameter tool.

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 opens with a clear directive: 'Read this server's capabilities before selecting analysis or execution tools.' It names the resource (server capabilities) and the specific verb (read), and it distinguishes the tool from siblings by stating it is a prerequisite step before choosing other tools. The subsequent sentences enumerate exactly what is returned (supported actions, automation modes, pause state, snapshot presence, revisions), which leaves no ambiguity about the tool's purpose.

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 first sentence explicitly states when to use this tool: 'before selecting analysis or execution tools.' It also clarifies the server's scope ('analyzes imported data and executes synthetic demo actions only'), which helps an agent understand what capabilities to expect and when this tool is relevant. The description also notes it 'Works before a snapshot is loaded,' giving a clear precondition. While it doesn't name a specific alternative tool, the context of sibling tools (e.g., get_source_status, get_manager_config) makes the usage context clear enough.

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