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

With no annotations, the description carries the full burden and does so well: it discloses ranking mechanism, that cached crossings are returned first and live traversal fills slots, and the cost of depth (one model call). It does not state auth/permission needs or result limits beyond the schema, but the operational behavior is unusually well surfaced.

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 purpose, then mechanism, then the routing rule against search_corpus. Every sentence contributes; no 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?

For a 6-param tool with no annotations and no output schema, the description explains the shape of the return (pre-computed bridge text, cached-first ordering) and the synthesis semantics, which is largely sufficient. It could be more explicit about result structure and limits, but the core is covered.

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 baseline is 3. The prose mentions the synthesized result and the deep-mode tradeoff but adds no parameter syntax or format detail beyond what the schema already documents for as_of, depth, limit, domain, and problem.

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?

Names a specific verb+resource ('Query the graph for synthesized insights') and details the scoring/selection mechanism, which makes the operation concrete. It differentiates against one sibling (search_corpus) but leaves overlap with other graph-reading siblings like traverse, navigate, and dig unaddressed.

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?

Explicitly states when to prefer it: 'Use this over search_corpus when you want synthesized insights, not a ranked list', and the depth param steers 'real problems, not dedup checks'. It gives a clear positive condition but no explicit when-not or guidance relative to the other query-like siblings.

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