Find nodes by their words

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

Annotations already establish read-only, non-destructive, closed-world behavior, so the description does not need to restate safety. It goes further by disclosing the ranking algorithm (title > note, node supporting more tree ranks higher, recency last) and that each result carries its lineage — genuinely useful traits not present in the annotations.

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?

Four sentences, front-loaded with the core action and filtering rule, then ranking, then the closed-node caveat. Mostly earns its space, though 'what you look for months later is usually finished' is slightly rhetorical padding.

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 carries the return-value burden and does so: it promises all matching nodes, best-first, each with its lineage. Ranking rules and the closed-node inclusion policy complete the picture an agent needs to interpret results.

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 coverage is 100%, so baseline is 3, but the description adds real semantics beyond the schema: matching is conjunctive across title/reason/note/outcome, which tells the agent to expect zero results for loose multi-word queries. The 'everywhere' flag's effect is left to the schema.

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 ('Search the provenance tree') and immediately scopes what is matched: nodes whose title, reason, note or outcome contains ALL terms. That distinguishes it from sibling read tools like vivac_why or vivac_brief, which serve different retrieval intents.

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?

Usage is implied rather than stated: 'what you look for months later is usually finished' signals the case where closed nodes matter, and the ranking note hints at search-vs-browse. But no sibling is named as an alternative and no when-not-to-use condition is given, so an agent must infer routing among the 14 vivac_* tools.

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