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

Annotations already establish read-only and idempotent behavior. The description adds critical context beyond annotations: results are never blended across corpora, rankings are within-corpus only, profile changes ordering/enrichment, and signals are qualitative with no market odds or investment advice. This is exactly the kind of behavioral nuance that helps an agent reason about outcomes.

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?

Three sentences, but each is information-dense and well-organized: first defines function and output structure, second gives usage conditions, third explains profile semantics and critical limitations. Slightly long but no filler; front-loaded with the core purpose.

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 covers input semantics (query, corpora, profile), output shape (per-corpus buckets), ranking behavior, and limitations. It lacks explicit pagination/error details, but for a search tool with no output schema, the description provides enough to set expectations and avoid misuse. Sibling differentiation is clear.

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 covers 80% of parameters with descriptions. The tool description enriches the meaning of `profile` by naming concrete behaviors (desk leads with signals via supporting evidence; publisher leads with news/declassified for citation), and `corpora` is explained as a comma-separated subset. The `vertical` parameter has no description and is not addressed, leaving a gap for a numeric-limited but non-trivial parameter.

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 opens with 'Search ALL of Storyflo in one call' — a specific verb and resource — and immediately clarifies the unique per-corpus bucketing behavior. It also distinguishes itself from siblings by positioning itself as the unified alternative to corpus-specific searches like search_articles and search_declassified.

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?

Explicitly states when to use: 'when you do not already know which corpus holds the answer, or when a topic spans several.' This implies the inverse condition (use corpus-specific search when you know the corpus), and it also explains profile-based use cases, offering practical guidance for selecting this tool over alternatives.

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