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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds substantial behavioral context: results are ranked by meaning rather than dumped, the catalog is too large to read wholesale, and each result carries inline correct-use metadata (signals, integrity_filter, edge_filter already applied by graph_neighbors, pit_column, coverage_rows, freshness). The freshness note explaining live vs nightly-materialized-view directly affects how an agent interprets walk currency.

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 lead sentence is front-loaded and bolded so the core purpose lands immediately, and the handoff instruction closes the paragraph cleanly. It is dense with internal jargon (pit_column, integrity_filter, E5) that inflates length, but nearly every clause carries operational information.

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?

There is no output schema, so the description must describe return values — and it does, enumerating each result field and its purpose. For a beta read-only discovery tool with three optional parameters, an agent has everything needed to call it correctly and interpret the response.

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 still adds value by explaining that `query` is natural-language and ranked semantically, that omitting it lists all, and by giving concrete example phrasings ('board seats', 'M&A'). It adds little about `limit` or `node_type` 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 names a specific verb and resource — 'discover what's traversable', a semantic-search catalog of edge types from mars.graph_edge_catalog — rather than restating the title. It also distinguishes itself from siblings by naming graph_neighbors as the downstream consumer, so an agent can place it in the workflow without opening schemas.

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?

Usage context is explicit: call this before walking the graph, omit `query` to list everything, and feed the returned edge_type into graph_neighbors. The only gap is that no explicit 'when not to use this / use X instead' exclusion is stated for ambiguous cases like a targeted entity lookup.

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