search_decisions

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that the search is ranked, uses BM25 with specific field weights, and returns a structured dictionary. It also explains the min_score threshold. However, it does not explicitly state whether the operation is read-only or mention any side effects, permissions, or rate limits. For a search tool, the provided detail is substantial but not exhaustive, meriting a 4.

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 well-structured and front-loaded with the core purpose. It then provides field weights, arguments, and return format. While it is somewhat lengthy, every sentence adds useful information for an agent (especially the field weights, which inform query tuning). It could be slightly tightened, but 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 description is complete for an agent to call this tool correctly. It explains all parameters, the return dictionary structure, and the scoring mechanism. Given that this is a read-only search operation and no output schema is provided in the context, the description fully covers what an agent needs to know. No critical gaps remain.

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?

The schema description coverage is 0%, so the description must compensate. It does so comprehensively: each parameter is explicitly explained in the 'Args' section, including defaults and value ranges (e.g., min_score 0-1). This adds significant meaning beyond the raw schema, which only lists types and defaults.

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's function: 'Search for past decisions matching a query.' It specifies the resource (decisions directory), the method (field-weighted BM25), and the output (ranked results with relevance scores). This distinguishes it from sibling tools like get_debate or consult, which serve different purposes.

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 what the tool does but does not explicitly state when to use it over alternatives or provide exclusions. It implies usage for searching decisions, but no guidance on when not to use it (e.g., if you already have a thread_id, use get_debate). Sibling tools are not referenced. This leaves the agent to infer appropriate usage from the tool's purpose alone.

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