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

Annotations declare readOnly=false, idempotent=false, destructive=false, and openWorld=true, so safety is partly covered. The description goes beyond that by disclosing that this is a live billed request, that credits charged are reported in the result, that no model runs on the path, and that results are capped at ten with deterministic merging — all material behavioral facts an agent cannot get from the annotations alone.

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?

Two sentences with no filler, and the core behavior is front-loaded. The prose is dense with internal pipeline jargon ('Perplexity-high + Parallel-basic fan-out'), which is compact but not immediately parseable.

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 structure needn't be described. However, for a 17-parameter tool with low schema coverage and only one required field, the description omits guidance on the legacy fields, mode selection, and provider/credits tradeoffs, leaving an agent to infer too much from the schema alone.

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 17 parameters and only 41% schema description coverage, the description carries a real compensation burden but adds almost nothing parameter-specific. It never explains mode, providers, rails, strategy (even that the latter two are legacy), maxCredits, or the domain filters; the only loose mapping is 'ten-result cutoff' to the maxResults default.

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 ('Find sources') and then exposes the pipeline (fan-out, deterministic merge, dedup, lexical reranking, ten-result cutoff). 'No Locus-controlled model runs on this path' subtly distinguishes it from a model-backed research path, though it never names the sibling web_research, which would have made the boundary explicit.

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?

There is no stated when-to-use or when-not-to-use guidance and no explicit alternative named, despite siblings web_research, web_extract, and search_apis being obvious candidates to disambiguate against. The only usage signal is the passing note that it is a 'live billed request,' which hints at cost-awareness but not tool selection.

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