P&ID: Connectivity Graph

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

Annotations only declare readOnlyHint=true, yet the description discloses a full confidence model (1.0 catalogue, 0.95 payload, 0.6 tag/keyword, 0.6 for a stretched bubble, 0.3 line-touching), per-node source reporting, edge resolution outcomes including `dangling` hints, and the scope constraint that `scope="all"` never merges sheets. This is exactly the behavioral context annotations cannot carry.

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 text is dense but front-loads the core idea ('connectivity as it is, not as drawn') and then moves through Nodes, Ports, Edges, and the confidence caveat in a logical order. Every clause carries technical meaning, though the parenthetical confidences make it heavier than a selection-time read strictly needs.

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?

With an output schema present and readOnlyHint set, the description need not explain return shapes or safety, and it still goes beyond by explaining how nodes/edges are classified and scored. It is complete for calling the tool correctly, with only the lack of alternatives routing holding it back.

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 the schema already documents all five parameters and a baseline of 3 applies. The description adds genuine semantics for `scope` (never joins two sheets) and surfaces `stats.confidence_min`, but says nothing about tolerance, label_search, include_foreign or include_geometry beyond what the schema already states.

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 makes clear this tool produces a connectivity graph of a P&ID drawing, decomposed into Nodes (classified symbol INSERTs) and Edges (lines/polylines), which is a specific verb+resource. It does not explicitly name or contrast any sibling such as drawing_topology_check or pid_instrument_index, so a reader must infer its niche from the domain wording rather than a stated differentiation.

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 explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The only actionable hint is buried in the final clause about reading stats.confidence_min before trusting a foreign drawing, which is a quality gate rather than a routing rule.

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