collect_news

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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the description must carry the rest, and it does add real context: no model call (cost/latency shape), per-source coverage is durable, and incomplete windows remain pending rather than resolving. The explicit warning not to treat partial capture as evidence of a quiet market is exactly the kind of behavioral caveat annotations cannot express.

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 short sentences, front-loaded with the core action and followed by the limitation and its interpretation. Every sentence carries distinct information (what, what it is not, failure semantics). The aphoristic tone of the final clause is slightly cryptic but not wasteful.

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?

An output schema exists, so return values need not be explained, and with a single optional parameter the schema burden is light. Against that lower bar the description covers the mutation's side effect and failure semantics but leaves the relationship to source-management siblings (which sources get collected, whether pending items must later be normalized by another tool) unstated.

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?

With one parameter and 100% schema coverage, the schema already documents since as a timezone-aware ISO start that should be omitted only to resume coverage. The description adds no format, boundary, or fallback detail for that parameter, so it neither compensates nor harms. 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 verb+resource are present ("capture ... news providers and durable per-source coverage"), and "without a model call" distinguishes it from an LLM-driven ingest. However, "capture" and "fixed news providers" are jargon that leave the concrete action (fetch items from configured sources and record per-source coverage state) only implied, and nothing distinguishes it from siblings such as add_news_source, news_sources, or pending_news.

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 interpretation guidance for failures ("never infer a quiet market from this failure") but says nothing about when to call this versus add_news_source, news_sources, or pending_news. The only invocation guidance, "omit only to resume existing coverage," lives in the schema for the since parameter rather than the description. No prerequisites or exclusions are stated.

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