Search the web and keep only the relevant hits

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

With no annotations present, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It explains concurrency ('runs them concurrently'), deduplication ('dedupes by canonical url'), reranking ('reranks everything against your original query with Jev'), and backend-specific caveats ('Snippets are empty on the CLI backends; codex titles are model-transcribed'). This is rich, honest behavior context.

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 three dense sentences with no fluff. It front-loads the return shape and ordering, then covers mechanics and backend caveats. Every sentence adds information an agent needs.

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 an output schema is present and the description already covers return structure, concurrency behavior, deduplication, reranking, and backend-specific output quirks, an agent has enough context to invoke the tool correctly. No annotations are needed because the description itself is sufficiently comprehensive.

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 100%, so the baseline is 3. The description adds some process-level context around variants ('sieve proposes 2-4 query variants in code') and clarifies the query type ('plain-language query'), but the individual parameter meanings are already well covered by the schema descriptions, so this does not rise above baseline.

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 verb and resource: 'Search the web for a plain-language query and return [{url, title, snippet, probability}]'. It is easy to understand the tool's core function, but it does not explicitly differentiate from sibling tools jev_grep and jev_rank, so it falls just short of a 5.

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 intended use is implied by 'Search the web for a plain-language query', which suggests this is for web searches, but the description provides no explicit guidance about when to prefer jev_search over jev_grep or jev_rank, nor any exclusions. The usage context is inferable but not stated.

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