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

readOnlyHint=true already covers the safety profile, and the description adds real context beyond it: the catalog tracks the newest FrontMCP release so there is no version parameter, and it discloses exactly what each mode returns (a listing, SKILL.md plus sibling reference files, or a single reference file). It stops short of describing error behavior for an unknown name.

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-loads the mode rules, with every sentence carrying information. The opening sentence is somewhat dense with the parenthetical catalog identifier, but nothing is wasted and the routing guidance arrives before the caveats.

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 carries the burden of describing returns, and it does so for all three modes. What remains unstated is failure behavior (unknown skill name, bad file path) and whether listing output is paginated, which are minor for a read-only catalog 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?

Schema coverage is 100%, so the schema documents both parameters, but the description adds semantic value the schema does not: it explains that name alone pulls SKILL.md together with its adjacent reference files, and that file is only meaningful in combination with name. That conditional relationship is behavior, not just field naming.

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 and resource ('skills catalog ... instructions for building with FrontMCP') and precisely enumerates the three call modes: no name lists skills, name returns SKILL.md plus reference files, name+file returns that file. It is readily distinguishable from siblings like get_page or search_docs.

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?

It explicitly routes the agent to alternatives with conditions: 'for the docs themselves use search_docs or get_page, and for runnable code get_example.' The mode-selection rules (when name is absent vs present vs paired with file) are spelled out with no inference required.

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