source_filter

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds useful context about the tiering logic and filtering criteria, which goes beyond structured data. However, it doesn't disclose how the ranking works (scoring algorithm, ordering of output) or any limitations (e.g., what happens with unknown domains).

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 front-loaded with the core action and then provides a compact tier breakdown. It is efficient and wastes no words, though the tier definitions could be slightly clearer (e.g., what exactly qualifies as 'noise/scrapers').

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?

No output schema exists, so the description should ideally explain return values (e.g., filtered list, ranked order, tier labels). It also doesn't clarify how 'outdated news & stale tech filtering' works or what happens to sources that don't fit a tier. For a filtering/ranking tool with no output schema, this is a moderate gap.

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 description coverage is 100%, so both parameters are fully documented in the input schema. The description does not add any parameter-level details (e.g., expected structure of source objects, how company_domain influences filtering). Baseline 3 is appropriate when the schema carries the parameter burden.

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 opens with a precise verb triple (evaluate, rank, filter) and names the resource (web research sources). It also names the specific criteria (domain credibility, outdated news, stale tech), which distinguishes it clearly from siblings like evidence_validator or company_research that deal with research but not source ranking.

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 implies usage context (filtering research sources), but it does not explicitly say when to call this tool vs. alternatives like evidence_validator or company_research. The tier system gives implicit guidance on what it does, but not on when an agent should invoke it.

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