run_scout_agent

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

With no annotations provided, the description carries the full transparency burden. It discloses that the tool spawns an agent, returns a phased/cited report, and explains the meaning of quick/deep/oracle modes. However, it omits operational traits such as whether runs are synchronous, side effects, permissions, or ambiguity in gallery_intel's 'deploy into a public gallery' behavior.

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 front-loaded with a one-sentence summary, followed by well-formatted bullet lists for agents and modes. Every line earns its place; the 'Returns' line and the pointer to get_scout_run are useful and not redundant.

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?

The description covers the fundamental choices (agent, mode), what the tool returns, and how to retrieve results later, which is strong for an orchestrator. Since an output schema exists, omitting full return-field detail is acceptable, but the absence of guidance on how project_id/hackathon_id constrain the run is a notable gap.

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 description must compensate. It does explain the key enum values (agent_id and mode), but goal, query, top_k, enrich, project_id, and hackathon_id are entirely left to inference. For an 8-parameter tool, this leaves significant invocation ambiguity.

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 description opens with a specific verb and resource: 'Spawn a specialized scout agent and return its phased, cited report.' It then enumerates the exact agent variants and modes, making the tool's function unmistakable and distinguishing it from sibling get_scout_run by noting the report can be retrieved later.

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 clearly maps agent IDs to their purposes and defines the three mode depths, giving an agent strong contextual cues for when to invoke this orchestrator. It also names an explicit alternative for retrieval ('Retrieve later via get_scout_run'), but it does not explicitly state when to prefer this over the many other domain tools.

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