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

Annotations already declare readOnlyHint and non-destructive, and the description layers substantive behavior on top: which embedding backend is used, the live-index-then-chunk-index fallback order, and the full return shape with a critical interpretive caveat that indexed:false means never-indexed rather than no match. That caveat is exactly the kind of trap an agent would otherwise fall into.

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?

Dense but front-loaded: the mechanism comes first, then the fallback order, then the return contract. Every clause carries information, though the return-value sentence is packed with semicolons and could be split for faster scanning.

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 documents the return object and the meaning of its fields, which is the highest-value thing it could add. It is incomplete only on the input side (limit behavior) and on scoring/ranking behavior of 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 description coverage is 0% across four parameters, so the description carries the burden, but it explains none of them. owner/repo are only obliquely implied by 'per-repo', query semantics are assumed, and limit is never mentioned at all, so an agent gets no guidance on result caps or query formulation.

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: querying a per-repo vector index backed by Voyage embeddings or a hash fallback. The mention of embeddings and the two-tier index (code_embeddings then code_chunks) distinguishes it from keyword-oriented siblings like merjax_search_code and merjax_repo_search, though it never names those alternatives explicitly.

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 by describing the semantic-vector mechanism, letting an agent infer this is for meaning-based retrieval rather than exact-match search, and the fallback chain is spelled out. However, there is no explicit when-to-use or when-not-to-use guidance relative to the many search/explain siblings, which is the main gap.

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