search_fulltext

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

With no annotations, the description carries the full burden and does meaningful work: it discloses that a first search can register and index a new linked worktree, that subsequent searches reuse the last completed index, and that incomplete Git operations retain it. These are non-obvious side effects for a tool named 'search'. It stops short of permissions, limits, or result-shape behavior.

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 matching semantics and the repo/cwd precedence rule are front-loaded, and every sentence carries information. The later sentences on worktree registration and index reuse are dense and slightly elliptical, but they are not 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?

There is no output schema and no annotations, so the description must cover a fair amount, and it covers path resolution and indexing behavior well. It leaves gaps on query syntax, the meaning of limit, and what results look like, which matters for a search tool whose whole value is the result set.

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 50%: cwd and repo are documented in the schema, while limit and query are not. The description does add real meaning beyond the schema by explaining the repo-vs-cwd precedence and how each resolves (Git worktrees vs directory roots). It does not clarify query tokenization rules or limit behavior, so it only partially compensates for the coverage gap.

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 names a specific verb and resource ('Tokenized full-text keyword search') and immediately delimits the matching model against alternatives ('not literal substring or regex matching'). It is easy to distinguish from search_structural, but it never names search_hybrid or search_semantic, so the sibling differentiation is implied rather than explicit.

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?

It gives concrete guidance on how to point the tool at a target ('Supply repo ... or cwd ...; repo takes precedence'), which is genuine usage context. However, it never states when to choose this tool over search_hybrid/search_semantic/search_structural, leaving the primary routing decision to inference.

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