Search Harness Engineering & Agentic AI

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint, and the description adds genuinely useful behavioral context: ranked results, accent-insensitive matching, language coverage, and the composition of each hit (relevance score and matched fields). This goes beyond what the structured annotations communicate.

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, front-loaded with the core purpose, and each sentence earns its place: scope, behavior, output composition, and usage guidance. No filler or redundant restating of structured fields.

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 the search use case, behavior, result format, and follow-up action while the output schema covers return details. Given the tool's moderate complexity and strong annotations, this is complete and leaves no obvious gap for an agent to misuse it.

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 100% of parameters with clear descriptions, so the baseline is 3. The description adds a meaningful semantic nuance for the query parameter by explaining that it matches 'every language' and 'ignores accents,' so the user can query in their own words—extending beyond the schema's simple 'in any of en/es/pt'.

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?

Description states a specific verb+resource: 'Ranked keyword search across the whole corpus' and names the domains covered. It clearly distinguishes itself from sibling get_* and list_* tools by positioning search as the entry point for question-like queries.

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 says to use this tool 'before any get_* tool whenever you have a question rather than an identifier' and to follow up with the matching get_* tool for full detail. This provides direct when-to-use guidance and names the alternative tool category.

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