get_capabilities

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

With no annotations provided, the description carries the full burden and does so excellently. It explains the tool returns a catalog of callable tools, grouped by source, with a specific table view. This fully describes the tool's behavior—it's a read-only introspection tool with no side effects, which is clearly communicated.

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 three sentences with no waste. The first sentence defines the core purpose, the second explains grouping, and the third describes the table view. Every sentence adds distinct value, and it's efficiently 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?

For a zero-parameter, no-output-schema introspection tool with 17 sibling tools, the description is highly complete. It could optionally mention that the catalog changes dynamically based on configuration, but that's not a significant gap given the simplicity and self-evident nature of the tool.

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 input schema has zero parameters and the description confirms this implicitly by not mentioning any required inputs. The tool is purely getter/self-describing, so there is no parameter documentation needed beyond what the schema provides (100% coverage).

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 tool's purpose: it shows the registered tool catalog for the Moodle MCP server. It specifies the output format (grouped by core and plugin tools) and provides a sample table view with columns, making it unmistakably distinct from the sibling tools like list_courses or get_site_info.

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 explicitly says it returns 'currently callable tools', implying it should be used when an agent needs to discover what tools are available on this MCP server. It doesn't need when-not-to-use guidance because there is no sibling tool with overlapping functionality—this tool is uniquely for introspection of the tool catalog itself.

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