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

Annotations already carry readOnly/idempotent/no-destructive, so safety is covered; the description goes further with behaviors found nowhere else: bare numeric node_id resolution echoed as resolved_node_id, an edge-less-but-existing node reported distinctly from unknown, and out-of-scope params surfaced in ignored_params rather than silently dropped. This is exactly the extra context that prevents misuse.

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?

Front-loaded with the core action and DAG scope, and every clause conveys mode behavior, filter applicability, or edge-case handling. It is a single dense paragraph with stacked parentheticals, which is slightly harder to scan, but there is no filler to cut.

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 7-parameter, four-mode traversal tool with no output schema, the description covers return shape per mode (paths with CC-type sequence and purity; reachable nodes; direct parents/children), filter interactions, and input normalization. Nothing an agent needs to invoke it correctly is missing.

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; the description adds genuine meaning by stating that cc_types and max_depth apply to both path and adjacency walks ('runs a bounded typed walk over the backbone edges'), what the path results contain per path, and that homogeneous_only is path-only with ignored_params echoing. Much of that is mirrored in the schema text, so it is strong value-add rather than fully novel.

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?

Specific verb+resource: 'Walk the Coordination Topology lineage graph (precomputed lookups over the parent→child Coordination Connection DAG)' with the four modes enumerated inline. It explicitly distinguishes itself from the sibling get_topology ('for structural metrics or the whole-graph summary rather than walks, use get_topology'), so an agent can route without opening a schema.

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?

Gives an explicit when-not rule with the named alternative (get_topology for metrics/summary), and mode-by-mode scope so the agent picks path vs ancestors/descendants/neighbours correctly. Also states which filters apply to which mode, removing inference.

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