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

The description meaningfully goes beyond the all-false annotations by disclosing synchronous semantics ('Blocking'), tolerance for incomplete results ('best-effort'), and a specific side effect for storm mode ('creates a deep multi-perspective STORM agent research job in Postgres'). This is useful behavioral context beyond what readOnlyHint=false, idempotentHint=false, and destructiveHint=false convey. Minor gaps remain, such as whether standard mode has persistent side effects and what happens when wait_s expires.

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 compact: one front-loaded lead sentence followed by a scannable bullet list for 'method'. Slight redundancy exists — 'method selects the backend execution engine' restates what the lead sentence already implied via 'or STORM agent' — but overall every line earns its place and the structure aids comprehension.

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 core behavior and the two execution modes are explained, and the presence of an output schema reduces the need to describe return values in prose. However, the interplay between 'depth' and 'method' is never addressed, 'wait_s' semantics are unstated, and there is no mention of relative cost, side effects, or when blocking terminates. For a moderately complex tool with no annotation help, these are nontrivial gaps.

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?

With 0% schema description coverage, the description carries full responsibility for explaining parameters, but it only documents 'method'. 'depth' is completely unexplained and confusingly defaults to 'standard' alongside 'method', inviting ambiguity about their relationship. 'wait_s' is only self-evident from its name, and its timeout/polling behavior is never stated — so an agent cannot reliably choose values for three of the four parameters.

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, 'Blocking-best-effort research over SeaWeb's live crawl queue or STORM agent,' states a specific operation with named backend resources and behavioral qualifiers ('blocking', 'best-effort'). The 'method' section adds concreteness by spelling out the two execution engines. It is distinguishable from siblings like research_status, search_web, and search, though it never names them explicitly.

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 gives real selection guidance for the 'method' parameter: 'standard' for the existing SQLite crawl queue and 'storm' for deep multi-perspective research jobs. However, there is no when-to-use vs alternatives guidance — nothing tells the agent when to prefer research over search_web, search, recall, or get_details, nor any exclusion criteria.

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