docs

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

With no annotations, the description carries the behavioral burden. It discloses the default output (run primer, namespace table, topics), how topic and search alter results, and that long answers come as 'a window plus a ref for expand_result.' It does not explicitly state that the tool has no side effects, but 'SDK reference' and the contrast with run make the read-only nature reasonably clear.

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 description is dense but efficient, with no filler and the core purpose front-loaded. It is slightly run-on with semicolons, but each clause carries meaningful information about modes, scope, or relationships to sibling tools.

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 read-only reference tool with two optional parameters and an output schema, this description covers the default behavior, all parameter modes, the SDK-version guarantee, and the relationship to run and expand_result. Nothing needed to invoke it correctly is missing.

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 description adds value beyond the schema by giving concrete topic examples (assets, project.apply, rooms, local-state), clarifying search as 'sections containing every word,' and explaining the expand_result link for long answers. This is more than the schema alone provides.

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 first sentence identifies docs as 'the SDK reference for run snippets,' and the final sentence explicitly contrasts it with run ('Any other operation is a run snippet... docs is its reference'). This gives a clear verb-adjacent purpose (reference/lookup) and distinguishes it from execution tools.

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?

The description explicitly divides labor: docs is for looking up SDK reference, run is for executing operations against r, and expand_result is the companion for long answers. It also spells out the invocation modes (no args, topic, search), so an agent knows exactly when and how to use this tool.

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