related_get

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), so the description adds the more useful missing piece: the shape of each returned item (type, id, title, subtitle, status, date, href). It stops short of saying whether results are grouped, limited, or truncated.

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 core claim is front-loaded in the first clause, followed by a dense but scannable per-type enumeration, then return shape, then usage. It is long, but nearly every clause carries information an agent needs; the four-way enumeration is the only part that borders on verbosity.

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 no output schema, the description correctly compensates by describing the per-item fields and the web link. For a read-only graph lookup with a fully documented schema, this is close to complete; only result size/capping behavior and any grouping are unstated.

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, but the description goes beyond it by explaining what the 'type' value actually means in terms of traversal (client → dosare/invoices/declarations, invoice → client/dosar/siblings, etc.). 'id' and 'companyId' add nothing beyond the schema, but the type semantics are genuinely enriched.

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 ('everything connected to one record') and then enumerates exactly what is returned for each of the four main record kinds. An agent can immediately distinguish this graph-traversal tool from siblings like invoices_get, dosare_get, or clients_get.

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 frames the use case ('answer "what else do we have about X?"') and names the alternative it replaces ('before searching list by list'). It does not say when to prefer the detailed single-record getters over this overview, so no explicit exclusion, but the routing guidance is clear.

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