semantic_search

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

With no annotations, the description carries the full burden and it discloses a significant hidden behavior: an automatic staleness check plus incremental re-indexing of changed files (a write side effect) with a stated freshness bound of one scan interval. It omits cost/latency, permission requirements, and failure behavior, which keeps it below a 5.

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?

Front-loaded with purpose and priority, followed by behavior and a compact Args block; almost every sentence earns its place. The Args list is terse rather than well-structured, and 'THE hot path' is stylistic, but nothing is wasted.

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?

An output schema exists, so return values need not be described. Given four parameters at 0% schema coverage, the description adequately documents param meaning and the key side-effect behavior, leaving only minor gaps (limit semantics, performance/error characteristics).

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%, so the description must compensate, and it explains three of four parameters: query (natural language), project (optional path, omit to search all), and file_filter (substring/glob with a '*.py' example). Only 'limit' is named without explanation, though its meaning is self-evident from the name and default.

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 code search across indexed projects'), which is unambiguous and clearly distinguishable from the sibling management tools (add/remove/list/index_status/reindex_project). An agent can identify this as the retrieval tool without opening the 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?

Signals primacy with 'THE hot path' and explains that it auto-reindexes, which implicitly tells the agent not to call reindex_project first. It also notes that omitting 'project' searches all registered projects, giving conditional usage guidance, though it never explicitly names alternatives or when-not-to-use conditions.

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