build_proposal

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

With no annotations, the description carries the full transparency burden, and it delivers: it discloses parallel execution, ranking criteria, return format (JSON + Markdown), cost breakdown, an indicative-rates disclaimer, and graceful handling of failed provider legs. This goes well beyond a simple 'build a proposal' statement and is genuinely revealing about the tool's 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 a single, dense sentence that packs in the composite nature, parallel execution, ranking, output types, cost breakdown, disclaimer, and failure handling. Every clause earns its place with no filler or repetition, making it both concise and information-rich.

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's complexity, the absence of annotations, and a missing output schema, the description covers a surprising amount: what the tool does, how it executes, what it returns, and how failures are handled. It falls short only on parameter-level guidance and explicit usage alternatives, which prevents it from being fully complete.

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 only 8%, so the description should compensate for the 12 parameters, but it does not. It only loosely references 'profile fit and budget' without explaining the actual parameter names, required fields, formats, or the semantics of options like maxStays or maxDining. This leaves the agent to rely almost entirely on the bare schema, which lacks descriptions for most properties.

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 a specific composite action: it runs stays, activities, and dining searches in parallel, ranks results by profile fit and budget, and returns both structured JSON and Markdown. It clearly distinguishes itself from sibling tools like search_stays and search_dining by presenting itself as a one-shot composite rather than a single-domain 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 phrase 'one-shot composite' clearly indicates this tool is for assembling a full proposal rather than searching a single category, which provides clear context for when to use it. It does not explicitly mention when not to use it or name alternatives, but the parallel-search framing and the sibling list make the intended usage reasonably clear.

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