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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral context beyond that: it reveals the approximate size of each doc (e.g., ~8KB card, ~4-5KB pattern cards), describes the content of each topic (e.g., 'shine/neon/glow technique rigs'), and notes that it returns text. This is a read operation, and the description confirms it returns text without side effects.

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 dense and front-loaded with the primary action ('Return a canonical Clipkit doc as text'). It then lists topics with concise but informative annotations. The structure is logical, though it could be slightly more scannable with line breaks or bullet points. Still, every sentence contributes value, and there is no fluff.

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 read-only tool with a single optional parameter, the description covers all necessary details: what the tool does, all possible parameter values, and when to use each. It also explains the reason for its existence (resources may not be model-readable). The only minor omission is an explicit statement about the return format (though 'as text' is mentioned), but that is sufficient. The description is complete for an agent to select and invoke the tool correctly.

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 schema only provides an enum and a brief description ('Which doc. Default "agents".'), but the tool description thoroughly explains each enum value, including what content each doc contains and recommended usage. For example, it defines 'pattern-data-viz' as 'proven idioms: count-ups and bar rows'. Since the description adds substantial meaning beyond the schema, it fully compensates for the schema's minimal parameter documentation.

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 exactly what the tool does: returns a canonical Clipkit doc as text. It then enumerates the specific topics available (card, pattern-*, agents, protocol, brand), giving each a distinct meaning. This distinguishes it clearly from sibling tools that manipulate projects, such as add_element or create_project.

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 offers explicit usage guidance for each topic, including when to use the card ('recommended context for authoring'), when to load pattern cards alongside the card ('when the brief matches its archetype'), when to fetch the agents guide ('only when the card doesn't cover a need'), and even explains why it's exposed as a tool (resources are not always model-readable). This gives the agent clear decision criteria.

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