Get Research Direction

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

Annotations already cover readOnly, openWorld, idempotent, and non-destructive. The description adds valuable context beyond them: the two response shapes, that 'context' is default/recommended, and that 'full' is cheaper for basic metadata. This is useful behavioral detail about output size and cost trade-offs.

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 action and input forms, then a bulleted breakdown of view options. Structurally clear, though the parenthetical about context containing full-provided fields is slightly convoluted.

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 2-param read-only tool with an output schema, the description covers both parameters, the default view, and the response-shape trade-offs. It omits what the output schema already covers, which is appropriate. Minor gap: no mention of error behavior for invalid IDs.

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 0%, so the description must compensate, and it largely does: it explains the accepted formats for cluster_id_or_url (numeric ID or URL ending in the number) and the view enum semantics with defaults and cost trade-offs. The only gap is that the URL format is not exactly specified.

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 (Fetch) and resource (Lacuna research direction/cluster). It does not explicitly differentiate from siblings like get_hypothesis or get_direction_papers, but the resource noun 'direction/cluster' is distinct enough for an agent to route correctly.

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 explains the input forms (numeric ID or URL) and the view semantics, implying usage, but never states when to prefer this tool over get_direction_papers or search_lacuna. No exclusions or alternative-routing guidance is given.

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