trawl_run_agent

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

No annotations are provided, so the description must carry the full behavioral burden. It sketches a three-step pipeline but does not disclose that the providers allowlist can cause the call to fail, whether context comes from a default pool, how many chunks are used by default, or what the response contains. Calling it a 'local LLM' run is also somewhat inconsistent with the schema's support for remote providers.

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 a single compact sentence, front-loaded with the core action and then the processing steps. It is efficient but so terse that important operational details are absent rather than merely compressed.

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?

This is an agent-execution tool with five parameters, no output schema, and no annotations. The description should explain return behavior, provider-allowlist failure semantics, and the role of pool_name, but it leaves all of these to be inferred. An agent could invoke it, but it lacks enough context to predict outcomes or avoid configuration failures.

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 schema already documents all five parameters, including defaults and the provider allowlist. The description does not add syntax or meaning beyond the schema's own field descriptions, which is the baseline for high-coverage schemas.

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 names a specific verb and resource: it runs a Trove agent, searches context, applies an agent prompt, and generates a response. That clearly distinguishes it from sibling tools like trawl_agents_list and trawl_agents_get, which inspect rather than execute agents. The phrase 'with local LLM' is slightly misleading because the schema's providers parameter accepts remote providers such as kimi, gemini, haiku, sonnet, and opus.

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 says what the tool does but gives no guidance on when to use it instead of trawl_agents_get, trawl_search, trawl_summarize, or other execution paths. It also omits any prerequisites, such as needing a valid agent_name or a pool_name for context retrieval.

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