Latest dispatches

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

Beyond the readOnly/openWorld annotations, it explains DOWN means unknown rather than no activity, CUT indicates truncation, CROSS is arithmetic and not a ranking, ordering is not importance, and teasers are marked and are not the article. This is exactly the behavioral nuance an agent needs.

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 but every sentence earns its place, with the core purpose front-loaded and caveats organized into digestible paragraphs. It avoids filler while covering crucial edge-case meaning.

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 an optional-parameter read tool with an output schema, it covers the domain caveats, the headline/full modes, language coverage, and how to proceed to wire_read. An agent can call it safely with defaults or with an informed detail/limit_per_source choice.

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 0%, so the description carries the burden. It explains detail values and the effect of raising limit_per_source, but it leaves hours, since, sources, and max_tokens to their schema properties with no added semantics beyond 'time window'.

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 opening states precisely what the tool returns: recent dispatches from 19 tech/AI sources in a time window, grouped by source and ordered newest-first within each. It also distinguishes itself by language scope and by positioning wire_read as the follow-up for article text.

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 gives clear usage context: this is a date-only, unranked view and the CROSS metric is an early-signal indicator, not a ranking. It names wire_read for the next step, though it does not explicitly contrast with wire_search or state when to choose wire_latest over it.

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