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

With no annotations, the description carries the behavioral burden, and it delivers: it explains that BACKGROUND edges are excluded by default because they would merge the corpus, that out-of-scope edges are counted but never followed, and that the operation is deterministic with no model call. It does not describe the output shape or side-effect profile, but the read-only graph-computation nature is clear.

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 but not bloated; the core graph concept is front-loaded, and each subsequent sentence adds relevant behavioral or scoping information. It could be trimmed slightly, but no sentence is filler.

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 edge types, scoping, default exclusions, boundary behavior, accepted document identifiers, and determinism. It does not explicitly state the return structure, and there is no output schema, but for a graph-components query the description gives enough context for an agent to invoke it correctly.

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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it specifies that `document` accepts a uuid, arXiv id, or node id, clarifies what `include_background` does to component structure, and explains the semantic difference between `connected_outside_only` and isolated. This extra context justifies a score above baseline.

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 by defining the tool's exact purpose: connected components of a record graph over reasoning edges. It names the specific edge types and explicitly contrasts 'computed' with 'filtered', making the resource and operation unmistakable. This is specific enough to stand apart from sibling search and retrieval tools even without naming them.

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?

It gives concrete scoping guidance: scope to a document or run, or omit both for the corpus. It also documents the default exclusion of BACKGROUND edges and explains the behavior for edges leaving the scope. It does not explicitly name alternative tools or when not to use this one, so it stops short of a 5.

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