adaptive_retrieve

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

No annotations are provided, so the description carries full burden. It discloses the iterative process, stopping conditions (coverage or token expansion), and that it is purely symbolic with no LLM required. It does not mention side effects or output format, but the read-only nature is implied.

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?

Two sentences efficiently convey the purpose, algorithm, and key behavioral traits. No wasted words; front-loaded with the title and process description.

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?

Given the tool complexity (5 parameters, no output schema), the description covers the core algorithm and stopping conditions. It lacks details on return format or result structure, but for a retrieval tool, the provided information is sufficient for basic usage.

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 only 20% (only budgetTokens has a description). The description does not detail individual parameters but explains the overall algorithm, which helps interpret the roles of query, maxRounds, minCoverage, etc. This partially compensates for the lack of schema descriptions.

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 clearly states the tool runs iterative query-rewriting retrieval, outlining the steps (search → score coverage → rewrite) and specifying it is purely symbolic without an LLM. This distinguishes it from sibling tools like semantic_search or hybrid_search.

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 algorithm and stopping criteria but does not explicitly guide when to use this tool versus alternatives. It implies use for multi-round retrieval to improve coverage but lacks explicit when-to-use or when-not-to-use instructions.

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