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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely new behavior: the output is a self-contained markdown briefing, it may be truncated to a token budget, and a final JSON line reports included ids, truncation status, and token count. Missing only details like ranking behavior or what happens when the budget is too small to fit even seeds.

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?

Four tight sentences, front-loaded with the core action and artifact, followed by output-format details and the input constraint. Every sentence carries information an agent needs; 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?

With no output schema, the description steps up to explain the return shape (self-contained markdown plus a final JSON line with ids/truncated/token count) and the invocation constraint. Together with annotations covering safety and the schema covering parameters, an agent has everything needed to call it correctly.

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 baseline is 3; the description adds value beyond the schema by stating the cross-parameter constraint that at least one of `query` or `ids` must be supplied — a requirement not encoded in the schema (required: []). It does not further explain depth, product, or tokenBudget semantics beyond the schema, so it is not a 5.

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 (assemble) and a specific artifact (markdown briefing of concepts expanded through the graph), plus the scoping inputs (query/ids) and the trimming constraint. It is clearly distinguishable from siblings like search_concepts, get_concept, and get_related, which return raw concepts rather than a budgeted bundle.

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?

Provides a concrete usage context — self-contained briefing to hand to another agent or paste into a prompt — and an explicit input constraint ('Provide at least one of `query` or `ids`'). It does not name sibling alternatives or state when not to use it, so it falls short of a full routing guide.

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