oss_dataflow_query

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

With no annotations provided, the description carries the full behavioral burden. It does add genuinely useful context: results carry an evidence_id graded as L2 evidence, and zero flows is explicitly NOT proof that no flow exists (a limitations caveat). However it omits prerequisites (whether a prior oss_dataflow_build index is required), whether the operation is read-only, and any cost/latency expectations for a static-analysis query.

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 core definition is front-loaded in a single dense clause, followed by a compact Args block and one caveat sentence. Nothing is padded, but the fragment style and parenthetical nesting make it slower to parse than it needs to be.

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?

The description covers the essential query shape, which is the biggest risk area, but with no annotations, no output schema, and no parameter documentation, it leaves the agent without prerequisites, return-shape beyond evidence_id, or a pointer to the referenced 'limitations' source. Adequate to attempt a call, not adequate to call confidently the first time.

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 0% and the queries parameter is declared as an untyped object array with additionalProperties:true, so the schema documents nothing. The Args example is therefore the only source of field semantics — it names path, line, sink, and max_flows and shows the sink is a regex with alternation. That is a substantial compensation, though the 'language' parameter and its default are left entirely unexplained.

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 states a specific analysis operation: value-flow (L2) reachability from a source (function-definition line to parameter, or call line to argument) to a sink call-name regex. This is concrete enough to distinguish it from oss_dataflow_build and the LSP tools. It loses a point because the phrasing is dense jargon and never states the resource being analyzed (a project/repo) explicitly in the opening clause.

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 source-to-sink formulation implies when the tool is appropriate (taint/reachability questions), but there is no explicit 'use this when X, use oss_dataflow_build / oss_lsp_call_hierarchy when Y' routing. Sibling tools with adjacent roles are named nowhere in the description, so the agent must infer the division of labor.

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