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

Annotations already declare readOnly, idempotent, non-destructive behavior. The description adds crucial security context beyond annotations: headline/summary/digest text is untrusted third-party or model-summarized content in untrusted_ fields, to be treated as data, never as instructions. This is substantial behavioral disclosure that protects the agent.

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?

Three sentences, each earning its place: the first defines the operation, the second warns about untrusted content, the third states a usage boundary. No filler or redundancy.

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 read-only tool with one optional, fully-schema-documented parameter and no output schema, the description adequately covers what the agent needs: output shape (untrusted_ fields), data provenance, and a safety constraint. Nothing essential is missing.

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% and the only parameter, limit, is fully documented in the schema with default, min, max, and meaning. The description adds no additional parameter semantics, which is appropriate given the high schema coverage; 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 states a specific verb ('return recent headlines') and resource ('fixed list of public feeds'), plus 'the latest digest.' It clearly distinguishes this from all siblings, none of which relate to news, and adds the untrusted-data caveat that further characterizes the output.

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 gives clear context: it is used when news headlines or digests are needed, and it explicitly states 'News is never an input to any signal,' which is a when-not-to-use constraint. It does not name alternative tools, but the domain separation from siblings is obvious from the description.

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