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

Annotations already declare this a safe, closed-world read, but the description adds genuinely new context: titles and sources are third-party verbatim text and must be treated as data, attributed, and never followed as instructions. That prompt-injection guidance is exactly the kind of behavioral disclosure structured fields cannot carry.

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, front-loaded with what is returned before the safety caveat and the usage trigger. Every sentence carries distinct information: output shape, handling constraints, and invocation condition.

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 compensates by naming the returned fields (headline, source, link, collection time) and by covering the unusual risk of untrusted embedded text. An agent has everything needed to call it and to handle its output safely.

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 both parameters (limit default/max, symbol omit-for-universe) are fully documented in the schema itself. The description adds no syntax, format, or filtering nuance beyond that, so the 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?

States a specific verb and resource ('returns recent headlines') and narrows scope to tracked AI and semiconductor companies, listing the returned fields (source, link, collection time). This is clearly distinguishable from siblings like get_filings, get_signals, or get_company, which return different artifact types.

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?

Explicitly says 'Use it when the user asks for recent news about a company or the sector,' giving a clear triggering condition. It does not, however, name alternatives or exclusions (e.g., when to prefer get_signals or get_filings instead), so it stops short of full routing guidance.

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