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

With no annotations, the description carries the behavioral burden. It tells the agent the tool returns the complete source file rather than a summary, and frames it as copyable working code; 'Return' signals a read operation. It doesn't mention error cases, but for a simple getter this is adequate.

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?

One sentence front-loads the action and object, gives a concrete example, and appends a clarifying contrast ('not a summary'). Every phrase earns its place with no redundant filler.

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 single-argument read tool with no output schema, the description tells the agent what it will receive (full .svelte source) and how to target a demo. It could additionally mention what happens for unknown ids, but overall the definition is complete enough for correct invocation.

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 already describes the single 'id' parameter at 100% coverage, including the same example. The description adds no new parameter-level detail beyond repeating the id/keyed-by-id concept, so baseline 3 applies.

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 ('Return') and identifies the exact resource: the full '.svelte' source for one demo, keyed by id. It even gives a concrete example and clarifies that it is not a summary, which distinguishes it from generic fetch/list/search siblings.

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 clearly states the context for calling this tool: you need the full source code of a specific demo by id. It doesn't name alternatives like list_examples or search, but 'one demo by id' and 'not a summary' provide enough scope guidance for selection.

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