cross_search

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

Annotations already provide readOnlyHint and idempotentHint. Description adds behavioral detail: snapshot-strictness and that results include freshness details per source. No contradictions.

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?

Two efficient sentences. First states purpose and result format, second provides usage guidance and alternative. No redundancy.

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?

Adequate for high-level understanding and usage decision, but lacks detail on parameter semantics. Output schema existence partially compensates for return value expectations.

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?

Description fails to explain parameters beyond the term (projectId, projectRef, limit, verbosity). With 0% schema description coverage, the description should compensate but does not.

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?

Description clearly states it searches a term across multiple code artifacts (code chunks, schema, RPC, routes, memories) and returns grouped indexed evidence with freshness details. It distinguishes itself from sibling tool live_text_search by noting it is snapshot-strict.

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?

Explicitly says when to use this tool (snapshot-strict search) and when to use the alternative live_text_search (for live disk fallback on recent/unindexed files).

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