flow_skeleton

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

With no annotations provided, the description carries the full disclosure burden. It does well by disclosing the output type (leads, not verdicts), the two modes, and the difference in behavior with no args vs scoped args. It falls slightly short of 5 by omitting any details about pagination, error, or order behavior beyond the default statement.

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 and heavily front-loaded: it states the core distinction in the first sentence, then adds kind definitions and parameter scoping in a compact way. Each sentence contributes meaningful information; there is no filler or repeated material.

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 a complex tool with no output schema, this description covers the conceptual model, output type, parameter roles, and sibling alternatives well. It leaves some gaps around exact lead/shape format and pagination/ordering behavior, but the provided context is enough for an agent to make a correct call in most situations.

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 at 60%, so the description's manager is important. The description richly explains the semantics of the `function` and `kind` parameters and clarifies default behavior with no arguments. However, it does little to expand on `limit`, `offset`, or `format` semantics, relying on the schema and enumerations for those.

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 clearly states the tool's job: to compose per-function summaries into interprocedural flow skeletons and match shape patterns over them. It names two concrete skeleton kinds (REACH and TYPESTATE) and explicitly differentiates itself from the single-function `skeleton` sibling.

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 explicit usage context: use this tool when you need cross-function flow that `skeleton` cannot show; also states it returns leads, not verdicts, and points to `sources_of/reaches` for adjudication. Additionally, it explains how to scope output with `function` and filter with `kind`, and what happens when no arguments are provided.

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