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

Goes well beyond readOnlyHint/openWorldHint: it discloses exactly what comes back (node/edge counts, most-cited authorities, edge-type breakdown) and the cap guard — when the match set exceeds the cap you get a total count and a request to narrow, mirroring the Explorer UI. That is precisely the kind of truncation/limit behavior an agent cannot infer from annotations or schema.

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 one-sentence purpose, then return shape, then the cap guard, then the Args list. The Args block is long but justified at 0% schema coverage; 'default 500, max 500' slightly duplicates the schema default but also adds the max, so it earns its place.

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 14 optional params, no output schema, and only two annotations, the description supplies the two things structured fields cannot: what the return payload contains and what happens at the cap boundary. An agent has enough to call it and interpret the result without trial and error; only filter-combination semantics remain implicit.

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 0%, so the Args block carries the full load and does it well: examples for query, domain, court codes, the six disposition values, jurisdiction strings, multi-select topics, substring-match semantics for claimant/respondent/appeal_from, and cap's default/max. Minor shortfall: it doesn't say how year_from/year_to interact or whether filters combine as AND, and the null defaults are never explained.

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?

States a specific verb and resource: return a filtered citation subgraph, plus the intended activity (graph exploration). An agent can tell this is the graph-shaped counterpart to search_cases from the 'same filters as search_cases' line, though it never explicitly contrasts itself with the sibling get_citation_network, which an agent must disambiguate on its own.

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 says to use the same filters as search_cases and explains the narrow-your-filters fallback, which gives implied usage context. But it never states when to choose this over get_citation_network, get_related_authorities, or top_authorities_in_domain — a real gap given six graph-adjacent siblings.

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