trawl_summarize

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

No annotations are provided, so the description carries the full burden. It discloses that an LLM is involved (implying cost/latency and non-determinism) but says nothing about expected latency, whether the synthesized output can drift from the source results, failure behavior, or whether the underlying search is read-only.

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?

A single short sentence with the action front-loaded and no filler. It is efficient, though the brevity is the source of the ambiguity noted elsewhere rather than being purely virtuous.

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 4-parameter tool with no annotations and no output schema, the description should explain what a 'concise summary' looks like, whether original results are also returned, and how it relates to the plain search tools. None of that is present.

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 all four parameters (query, top_k, pool_name, providers) are already documented in the schema, including the provider allowlist failure semantics. The description adds no additional meaning beyond that, which is the baseline-3 case.

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?

It names a specific verb pair (search + return summaries) and the LLM mechanism, so the action is identifiable. But 'results' is undefined and the description never distinguishes it from the many search siblings (trawl_search, trawl_search_pool, trawl_search_multi), so an agent cannot confidently choose it over them.

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?

There is no statement of when to prefer this over plain retrieval tools, nor any exclusion. With over a dozen search-related siblings, the absence of any routing guidance is a real gap.

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