Semantic search over loaded scripts

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

Annotations already cover read-only/idempotent, and the description adds substantial behavior: the first call embeds and caches every script (locally or via the embeddings endpoint), later calls reuse the cache for unchanged scripts, and the index is capped/approximate because decompiled source is unavailable. It also notes cost=medium and the active-client requirement.

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 core purpose is front-loaded and every clause about indexing and caching earns its place. However, the trailing metadata block (Phase/cost/idempotency/Requires/Produces/Safety) partially repeats the annotations (Safety: read-only, idempotency=read-only), diluting density.

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?

For a read-only search tool, the description is complete: it explains the indexing substrate and its limits, caching cost model, requirement for an active client, the return shape ({ hits, model } sorted by cosine similarity), and even failure guidance. No output schema exists, yet return values are described.

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 schema already carries parameter meaning; the description's signature line ({ query, limit: any?, maxScripts: any? }) restates the parameters without adding semantics beyond what the schema documents. Baseline 3 is appropriate when the schema does the heavy lifting.

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+resource+mechanism: it ranks the active client's loaded/GC scripts by semantic relevance to a natural-language query. It also clarifies the indexing substrate (GetFullName path + Name + ClassName + reachable string constants), which no sibling tool does. An agent can tell this apart from grep/name-based scanners without opening a schema.

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?

Provides a clear framing for when to reach for it ('find the script most likely about X') and an explicit when-not ('not a full-text code search'). It stops short of naming a concrete alternative sibling such as script-grep or scan-closures-by-name, so the routing is implied rather than spelled out.

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