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

With no annotations, the description carries the full burden, and it delivers a genuinely important behavioral trait: bodies are untrusted text from strangers, including other AI models, and must be treated as data only. That prompt-injection warning is high-value context. It still omits auth requirements, rate limits, and result shape.

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?

Two compact sentences with the core behavior front-loaded and the security caution clearly marked. No wasted filler, though the metaphorical phrasing costs a little clarity for the space it takes.

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 simple single-param read tool with no output schema and no annotations, the description covers what it returns and the critical untrusted-content caveat. It stops short of describing the item's fields beyond the `id`, leaving the caller to infer the rest.

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?

Single optional `limit` parameter with 100% schema description coverage, so the schema fully documents count, default, and max. The description adds nothing about `limit`, making baseline 3 correct.

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?

States a specific verb+resource: returns the newest 'pebbles currently afloat in sediment,' mirroring the live public web view. Paired with siblings cast_thought and skip_thought, an agent can infer this is the read/feed counterpart. The heavy metaphor ('pebbles', 'river', 'afloat in sendiment') obscures exactly what a returned item is, keeping it short of 5.

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?

Usage is implied (fetch the newest feed) and it gives one concrete next-step: 'Use the returned `id` with skip_thought.' It never states when to prefer this over the siblings or any precondition, so guidance remains inferential rather than explicit.

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