search_multiple_phrases

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

No annotations exist, so the description carries the full burden of behavioral disclosure. It does disclose meaningful traits: results are deduplicated/merged by stable UID, evidence tiers are deterministic, and the tool does not automatically browse candidates. It stops short of stating read-only status, response format, or edge-case behavior like zero matches, but the disclosed traits are specific and genuinely informative.

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 with zero filler. The primary action is front-loaded and the exclusion of auto-browsing is appended as a single clarifying clause. Every word earns its place.

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 tool has a complex nested schema (MultiPhraseInput with filters, search_mode enum, responsa_options), no annotations, and no output schema. The description explains the core search-and-merge behavior but leaves critical invocation decisions unresolved — notably what each search_mode means, when filters apply, and what the evidence tiers represent. An agent cannot reliably choose correct parameter values from this definition alone.

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 0%, so the description must compensate. It only clarifies the `phrases` parameter ('up to five distinct phrases', mapping to maxItems: 5). It says nothing about `search_mode` (exact/variants/responsa), `limit_per_phrase`, the rich `filters` object with eight sub-fields, or `responsa_options` — leaving an agent to guess the meaning and correct values of most 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 description states a specific verb and resource ('Search up to five distinct phrases') and adds a distinctive behavioral outcome ('merge candidate pages by stable UID into deterministic evidence tiers') that sets it apart from search_manuscripts (manuscripts vs. pages) and browse_page ('does not browse candidates automatically'). An agent can tell what this tool does without opening the schema.

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 final sentence 'This does not browse candidates automatically' is a negative qualifier that steers the agent away from expecting browsing behavior, implicitly pointing toward browse_page as the alternative. However, there is no explicit statement of when to use this tool versus search_manuscripts or find_parallels, so the usage context is implied rather than clearly routed.

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