ov_search

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new behavioral context: the matching is semantic ('by meaning') rather than keyword, and it discloses the shape of results. It omits anything about result-set behavior when nothing matches, which is a minor gap.

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 capability, then return shape, then the usage rule. No sentence is redundant or restates the tool name.

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?

With no output schema, the description usefully compensates by naming the three returned fields. Four parameters and no nested objects makes this a simple tool, and the only thing an agent might still want — what happens on zero matches — is minor.

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 query, limit, target_uri and score_threshold are all documented in the schema itself, including the subtree URI example. The description adds nothing parameter-specific beyond the vocabulary overlap of 'URI' and 'relevance score' in the return statement, so baseline 3 applies.

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?

States a specific verb and resource — semantic search over the OpenViking knowledge base — plus the return shape (URI, relevance score, summary). It does not explicitly contrast itself with siblings ov_read and ov_overview, though the names plus 'search by meaning' make the distinction reasonably inferable.

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?

'Use it before writing SQL, DDL or node changes to check for existing standards and known pitfalls' gives a concrete triggering context, which is stronger than most. It stops short of explicit when-not conditions or naming ov_read/ov_overview as the alternatives for retrieval once a URI is known.

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